Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-05-15T20:34:08.207848Z
Paper Citation Record · LEDGER
Discovering Latent Knowledge in Language Models Without Supervision
As of 6 August 2026, this Paper Citation Record lists 44 of 44 outbound references and 94 inbound Pith citation observations for arXiv:2212.03827.
A citation records a reference. It does not transfer a finding from one paper to another.
Coverage vector
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-06T06:34:29.942622+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links, observed 2026-08-06T15:14:16.689102Z
A source-named dated measurement, never combined with another source.
Source: pith, observed 2026-08-05T02:28:24.338817Z
Reference resolution
44 of 44 outbound references displayed
- verified exact25
- verified fuzzy10
- unresolved0
- parse uncertain0
- malformed identifier0
- metadata mismatch9
External citation measurements
45
pith, observed 2026-08-05T02:28:24.338817Z
Outbound references
Observation 7054bd77-617c-4b80-8bfd-00518389ec30 · outbound
This paper cites A General Language Assistant as a Laboratory for Alignment.
Discovering Latent Knowledge in Language Models Without Supervision A General Language Assistant as a Laboratory for Alignment
Reference 1
- Resolution
- verified exact
- local_arxiv, observed 2026-05-15T20:34:08.305675Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 33d77505-15b6-4fe6-93ce-2a5dfb2592dd · outbound
This paper cites Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback.
Discovering Latent Knowledge in Language Models Without Supervision Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback
Reference 2
- Resolution
- verified exact
- local_arxiv, observed 2026-05-15T20:34:08.237537Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation e7b72cc2-45c0-47b2-95a7-a421c5a34e29 · outbound
This paper cites Bender, Timnit Gebru, Angelina McMillan-Major, and Shmargaret Shmitchell.
Discovering Latent Knowledge in Language Models Without Supervision Bender, Timnit Gebru, Angelina McMillan-Major, and Shmargaret Shmitchell
Reference 3
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-15T20:34:08.352984Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 41f2e11f-2b54-4efb-abe6-81569996d8c1 · outbound
This paper cites On the Opportunities and Risks of Foundation Models.
Discovering Latent Knowledge in Language Models Without Supervision On the Opportunities and Risks of Foundation Models
Reference 4
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-15T20:34:08.278904Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation c402b99c-6335-44fc-b359-d92a8708faba · outbound
This paper cites Language Models are Few-Shot Learners.
Discovering Latent Knowledge in Language Models Without Supervision Language Models are Few-Shot Learners
Reference 5
- Resolution
- verified exact
- local_arxiv, observed 2026-05-15T20:34:08.284137Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 316431e8-35a7-4f2f-b5c6-35f228550c4d · outbound
This paper cites Deep reinforcement learning from human preferences.
Discovering Latent Knowledge in Language Models Without Supervision Deep reinforcement learning from human preferences
Reference 6
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-16T08:39:30.882444Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation bc95caa8-bb73-4a7e-b699-88e094c64a50 · outbound
This paper cites Supervising strong learners by amplifying weak experts.
Discovering Latent Knowledge in Language Models Without Supervision Supervising strong learners by amplifying weak experts
Reference 7
- Resolution
- verified exact
- local_arxiv, observed 2026-05-15T20:34:08.291275Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 5698c28a-791c-4963-9f57-c48273c6b764 · outbound
This paper cites BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions.
Discovering Latent Knowledge in Language Models Without Supervision BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions
Reference 8
- Resolution
- verified exact
- local_arxiv, observed 2026-05-15T20:34:08.294891Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 12269bc7-6dd8-4ba7-89e7-e45b05c82c0f · outbound
This paper cites Truthful AI: Developing and governing AI that does not lie.
Discovering Latent Knowledge in Language Models Without Supervision Truthful AI: Developing and governing AI that does not lie
Reference 9
- Resolution
- verified exact
- arxiv_id, observed 2026-05-15T20:34:08.298850Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 560aaf69-397e-4a37-9c29-567103800a68 · outbound
This paper cites DeBERTa: Decoding-enhanced BERT with Disentangled Attention.
Discovering Latent Knowledge in Language Models Without Supervision DeBERTa: Decoding-enhanced BERT with Disentangled Attention
Reference 10
- Resolution
- verified exact
- local_arxiv, observed 2026-05-15T20:34:08.302421Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 5e200fab-3720-44fa-80e5-b0ff20d7eda9 · outbound
This paper cites Unsolved Problems in ML Safety.
Discovering Latent Knowledge in Language Models Without Supervision Unsolved Problems in ML Safety
Reference 11
- Resolution
- verified exact
- arxiv_id, observed 2026-05-16T20:45:28.030299Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 548d9f5b-f722-487f-8316-505edf7f8b12 · outbound
This paper cites AI safety via debate.
Discovering Latent Knowledge in Language Models Without Supervision AI safety via debate
Reference 12
- Resolution
- verified exact
- local_arxiv, observed 2026-05-15T20:34:08.308667Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation e76b8ba6-ed1d-4f2c-a0a5-65d7d0c74ac0 · outbound
This paper cites Maieutic Prompting: Logically Consistent Reasoning with Recursive Explanations.
Discovering Latent Knowledge in Language Models Without Supervision Maieutic Prompting: Logically Consistent Reasoning with Recursive Explanations
Reference 13
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-15T20:34:08.311916Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 5d0cd27f-e5b7-485f-ae64-cf47f5e8f508 · outbound
This paper cites Alignment of Language Agents.
Discovering Latent Knowledge in Language Models Without Supervision Alignment of Language Agents
Reference 14
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-15T20:34:08.315226Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation c03ffb76-70c4-487c-8b84-28b58ab7dc65 · outbound
This paper cites Ground-Truth Labels Matter: A Deeper Look into Input-Label Demonstrations.
Discovering Latent Knowledge in Language Models Without Supervision Ground-Truth Labels Matter: A Deeper Look into Input-Label Demonstrations
Reference 15
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-15T20:34:08.318512Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation f03c4e3a-47fe-4779-ad06-5deff716a1fa · outbound
This paper cites Adam: A Method for Stochastic Optimization.
Discovering Latent Knowledge in Language Models Without Supervision Adam: A Method for Stochastic Optimization
Reference 16
- Resolution
- verified exact
- local_arxiv, observed 2026-05-15T20:34:08.321324Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 838a7ba4-b93f-4f1f-9f8e-aa2f772f759b · outbound
This paper cites Scalable agent alignment via reward modeling: a research direction.
Discovering Latent Knowledge in Language Models Without Supervision Scalable agent alignment via reward modeling: a research direction
Reference 17
- Resolution
- verified exact
- local_arxiv, observed 2026-05-15T20:34:08.324344Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation ac205680-71ff-44e0-804c-a37f7454ead5 · outbound
This paper cites RoBERTa: A Robustly Optimized BERT Pretraining Approach.
Discovering Latent Knowledge in Language Models Without Supervision RoBERTa: A Robustly Optimized BERT Pretraining Approach
Reference 18
- Resolution
- verified exact
- local_arxiv, observed 2026-05-15T20:34:08.327577Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 475dc91b-c9e4-42ba-b257-490c63ef2b7c · outbound
This paper cites Decoupled Weight Decay Regularization.
Discovering Latent Knowledge in Language Models Without Supervision Decoupled Weight Decay Regularization
Reference 19
- Resolution
- verified exact
- local_arxiv, observed 2026-05-15T20:34:08.330770Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation e7e7ce69-a935-47ec-8949-7b84c00a5a3a · outbound
This paper cites On Faithfulness and Factuality in Abstractive Summarization.
Discovering Latent Knowledge in Language Models Without Supervision On Faithfulness and Factuality in Abstractive Summarization
Reference 20
- Resolution
- verified exact
- arxiv_id, observed 2026-05-15T20:34:08.334377Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation c3a61323-0f87-4ad2-881d-0289e4a60ec9 · outbound
This paper cites Teaching language models to support answers with verified quotes.
Discovering Latent Knowledge in Language Models Without Supervision Teaching language models to support answers with verified quotes
Reference 21
- Resolution
- verified exact
- arxiv_id, observed 2026-05-17T11:45:48.341649Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 2b18b2f4-47b0-4b94-b739-f752e4157c55 · outbound
This paper cites MetaICL: Learning to Learn In Context.
Discovering Latent Knowledge in Language Models Without Supervision MetaICL: Learning to Learn In Context
Reference 22
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-15T20:34:08.341197Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 1583a627-e650-41c0-b44b-1d0cf97e21a8 · outbound
This paper cites WebGPT: Browser-assisted question-answering with human feedback.
Discovering Latent Knowledge in Language Models Without Supervision WebGPT: Browser-assisted question-answering with human feedback
Reference 23
- Resolution
- verified exact
- local_arxiv, observed 2026-05-15T20:34:08.344378Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation c95bebdc-9c95-457b-b97a-ebd6e96d1c0d · outbound
This paper cites Training language models to follow instructions with human feedback.
Discovering Latent Knowledge in Language Models Without Supervision Training language models to follow instructions with human feedback
Reference 24
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-15T20:34:08.347537Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 326f6614-903a-48fe-96a1-774af62f3fac · outbound
This paper cites Red Teaming Language Models with Language Models.
Discovering Latent Knowledge in Language Models Without Supervision Red Teaming Language Models with Language Models
Reference 25
- Resolution
- verified exact
- local_arxiv, observed 2026-05-15T20:34:08.350609Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 96809c38-c7d3-495c-b8ae-2ee028c92ed7 · outbound
This paper cites Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer.
Discovering Latent Knowledge in Language Models Without Supervision Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
Reference 26
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-15T20:34:08.242501Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation d69ab1c6-9bd7-46b7-9bea-97c93036c77b · outbound
This paper cites SQuAD: 100,000+ Questions for Machine Comprehension of Text.
Discovering Latent Knowledge in Language Models Without Supervision SQuAD: 100,000+ Questions for Machine Comprehension of Text
Reference 27
- Resolution
- verified exact
- local_arxiv, observed 2026-05-15T20:34:08.246766Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation e07a74a8-8a1d-4c2e-8c5d-5556d2523c75 · outbound
This paper cites Choice of plausible alternatives: An evaluation of commonsense causal reasoning.
Discovering Latent Knowledge in Language Models Without Supervision Choice of plausible alternatives: An evaluation of commonsense causal reasoning
Reference 28
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-15T20:34:08.367484Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 29f5c200-1097-4bf6-bd93-ed2299d2330e · outbound
This paper cites Multitask Prompted Training Enables Zero-Shot Task Generalization.
Discovering Latent Knowledge in Language Models Without Supervision Multitask Prompted Training Enables Zero-Shot Task Generalization
Reference 29
- Resolution
- verified exact
- local_arxiv, observed 2026-05-15T20:34:08.250101Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation a21247f0-bcbd-4776-84ee-cd02e05a69b1 · outbound
This paper cites Learning to summarize from human feedback.
Discovering Latent Knowledge in Language Models Without Supervision Learning to summarize from human feedback
Reference 30
- Resolution
- verified exact
- arxiv_id, observed 2026-05-18T01:46:18.838660Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation b05242b8-3f58-4cb6-b355-12ec5e3ff3aa · outbound
This paper cites FEVER: a large-scale dataset for Fact Extraction and VERification.
Discovering Latent Knowledge in Language Models Without Supervision FEVER: a large-scale dataset for Fact Extraction and VERification
Reference 31
- Resolution
- verified exact
- local_arxiv, observed 2026-05-15T20:34:08.258343Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation dac2e12b-a208-4dac-be6e-f423cf1e2fe6 · outbound
This paper cites GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding.
Discovering Latent Knowledge in Language Models Without Supervision GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding
Reference 32
- Resolution
- verified exact
- local_arxiv, observed 2026-05-15T20:34:08.261955Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 23635a30-246e-4ba9-b4e8-79ce61bc5709 · outbound
This paper cites Finetuned Language Models Are Zero-Shot Learners.
Discovering Latent Knowledge in Language Models Without Supervision Finetuned Language Models Are Zero-Shot Learners
Reference 33
- Resolution
- verified exact
- local_arxiv, observed 2026-05-15T20:34:08.265277Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 8b5fc1b9-5018-4f6b-9899-270224ad3412 · outbound
This paper cites HuggingFace's Transformers: State-of-the-art Natural Language Processing.
Discovering Latent Knowledge in Language Models Without Supervision HuggingFace's Transformers: State-of-the-art Natural Language Processing
Reference 34
- Resolution
- verified exact
- local_arxiv, observed 2026-05-15T20:34:08.268533Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 44ec5d43-9a94-4655-9930-48e61a3a461d · outbound
This paper cites Calibrate Before Use: Improving Few-Shot Performance of Language Models.
Discovering Latent Knowledge in Language Models Without Supervision Calibrate Before Use: Improving Few-Shot Performance of Language Models
Reference 35
- Resolution
- verified exact
- arxiv_id, observed 2026-05-15T20:34:08.272099Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation bab857f6-9b58-4109-b43c-69fa69990089 · outbound
This paper cites Prompt Consistency for Zero-Shot Task Generalization.
Discovering Latent Knowledge in Language Models Without Supervision Prompt Consistency for Zero-Shot Task Generalization
Reference 36
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-15T20:34:08.275559Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 93f9bf49-bd74-4324-a474-56a74bb934ea · outbound
This paper cites Is 2+2=4? Yes.
Discovering Latent Knowledge in Language Models Without Supervision Is 2+2=4? Yes
Reference 37
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-15T20:34:08.369552Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 44ae3498-4e2b-4f8d-b4be-4a3b20ebf014 · outbound
This paper cites hidden states.
Discovering Latent Knowledge in Language Models Without Supervision hidden states
Reference 38
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-15T20:34:08.371651Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 669c4cac-f670-41fb-99f1-d862ba1ceac1 · outbound
This paper cites [text] = I loved this movie.
Discovering Latent Knowledge in Language Models Without Supervision [text] = I loved this movie
Reference 39
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-15T20:34:08.354996Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 7e8f239f-3405-4df5-898c-b2342791e464 · outbound
This paper cites ‘ [content].
Discovering Latent Knowledge in Language Models Without Supervision ‘ [content]
Reference 40
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-15T20:34:08.357051Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation ee62ca3e-f61e-4b6d-a780-8e1243e6fc66 · outbound
This paper cites Here the label is a short sentence.
Discovering Latent Knowledge in Language Models Without Supervision Here the label is a short sentence
Reference 41
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-15T20:34:08.359284Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation d7abd8d6-dcc9-42a3-b49b-3cc077d35637 · outbound
This paper cites ‘ [premise].
Discovering Latent Knowledge in Language Models Without Supervision ‘ [premise]
Reference 42
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-15T20:34:08.361276Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 5b215f2e-1d43-44a0-bf79-6af2a0aa907d · outbound
This paper cites [label]” is “negative.
Discovering Latent Knowledge in Language Models Without Supervision [label]” is “negative
Reference 43
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-15T20:34:08.363341Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 4bf9e264-3cfc-4706-9089-47164b0a879e · outbound
This paper cites yes” or “no.
Discovering Latent Knowledge in Language Models Without Supervision yes” or “no
Reference 44
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-15T20:34:08.365373Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Pith citing papers
Observation 972a7f42-7d52-416a-9f5e-4c1a96b903d4 · inbound
The Internal State of an LLM Knows When It's Lying cites this paper.
The Internal State of an LLM Knows When It's Lying Discovering Latent Knowledge in Language Models Without Supervision
Reference 25
- Resolution
- verified exact
- local_arxiv, observed 2026-05-16T00:08:36.576016Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation a436c8ed-cd9c-44ce-ac8c-599dc9710c33 · inbound
A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions cites this paper.
A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions Discovering Latent Knowledge in Language Models Without Supervision
Reference 32
- Resolution
- verified exact
- arxiv_id, observed 2026-05-15T20:34:08.372263Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 5a4a42f7-f3a3-4b76-a8e5-d13a63289cfc · inbound
Refusal in Language Models Is Mediated by a Single Direction cites this paper.
Refusal in Language Models Is Mediated by a Single Direction Discovering Latent Knowledge in Language Models Without Supervision
Reference 123
- Resolution
- verified exact
- arxiv_id, observed 2026-05-15T20:34:08.372263Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation a856920c-44b4-4c1e-ac61-6f54e23e35f8 · inbound
Training Language Models to Self-Correct via Reinforcement Learning cites this paper.
Training Language Models to Self-Correct via Reinforcement Learning Discovering Latent Knowledge in Language Models Without Supervision
Reference 137
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-17T12:04:10.676680Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 99afcef3-01b2-451f-82c4-4b463a8691ba · inbound
Mechanistic Interpretability Needs Philosophy cites this paper.
Mechanistic Interpretability Needs Philosophy Discovering Latent Knowledge in Language Models Without Supervision
Reference 5
- Resolution
- verified exact
- local_arxiv, observed 2026-05-21T23:50:47.353935Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 8a1a899e-d56f-4157-9daa-0fef7608adf1 · inbound
NPO: Learning Alignment and Meta-Alignment through Structured Human Feedback cites this paper.
NPO: Learning Alignment and Meta-Alignment through Structured Human Feedback Discovering Latent Knowledge in Language Models Without Supervision
Reference 2000
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T15:14:16.689102Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 42cad935-733f-447c-b499-5832851180d8 · inbound
LENS: Learning Ensemble Confidence from Neural States for Multi-LLM Answer Integration cites this paper.
LENS: Learning Ensemble Confidence from Neural States for Multi-LLM Answer Integration Discovering Latent Knowledge in Language Models Without Supervision
Reference 4
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T11:03:16.510374Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 788a296d-7b76-4c98-8253-351e8993630b · inbound
A Survey on Data Security in Large Language Models cites this paper.
A Survey on Data Security in Large Language Models Discovering Latent Knowledge in Language Models Without Supervision
Reference 7
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T05:04:58.587323Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 208a2103-5324-43ae-af81-1de597b8beb4 · inbound
Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM cites this paper.
Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM Discovering Latent Knowledge in Language Models Without Supervision
Reference 224
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T23:13:05.279845Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 34721bb2-9705-4205-8fb2-c98b1cc3fd4e · inbound
Quantized but Deceptive? A Multi-Dimensional Truthfulness Evaluation of Quantized LLMs cites this paper.
Quantized but Deceptive? A Multi-Dimensional Truthfulness Evaluation of Quantized LLMs Discovering Latent Knowledge in Language Models Without Supervision
Reference 6
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T15:52:44.867137Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation e0d35989-fd01-498f-bf30-5a86313d7fc2 · inbound
STARE at the Structure: Steering ICL Exemplar Selection with Structural Alignment cites this paper.
STARE at the Structure: Steering ICL Exemplar Selection with Structural Alignment Discovering Latent Knowledge in Language Models Without Supervision
Reference 9
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T14:47:11.367586Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation d6239db5-d241-4e32-b4db-0f8ff4549ecf · inbound
Two Causes, Not One: Rethinking Omission and Fabrication Hallucinations in MLLMs cites this paper.
Two Causes, Not One: Rethinking Omission and Fabrication Hallucinations in MLLMs Discovering Latent Knowledge in Language Models Without Supervision
Reference 2023
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T13:44:11.202844Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation db747075-a0cc-407d-971f-457774cc3c43 · inbound
Can LLMs Lie? Investigation beyond Hallucination cites this paper.
Can LLMs Lie? Investigation beyond Hallucination Discovering Latent Knowledge in Language Models Without Supervision
Reference 4
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T10:55:31.201012Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 0965d9b4-8212-4343-8f0a-c922e0bfc76c · inbound
Cross-Layer Attention Probing for Fine-Grained Hallucination Detection cites this paper.
Cross-Layer Attention Probing for Fine-Grained Hallucination Detection Discovering Latent Knowledge in Language Models Without Supervision
Reference 3
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T10:18:02.808211Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 737f2084-1b16-47e0-85e0-155f7b7506aa · inbound
Unsupervised Hallucination Detection by Inspecting Reasoning Processes cites this paper.
Unsupervised Hallucination Detection by Inspecting Reasoning Processes Discovering Latent Knowledge in Language Models Without Supervision
Reference 4
- Resolution
- unresolved
- no resolver link, observed 2026-08-04T18:25:37.321564Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b92854d8-3d78-4b48-9f3d-f77b14696bae · inbound
HalluField: Detecting LLM Hallucinations via Field-Theoretic Modeling cites this paper.
HalluField: Detecting LLM Hallucinations via Field-Theoretic Modeling Discovering Latent Knowledge in Language Models Without Supervision
Reference 2015
- Resolution
- unresolved
- no resolver link, observed 2026-08-04T17:41:04.927879Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b9f8d589-fb1d-421f-b447-01e879dbc9e5 · inbound
Neural Message-Passing on Attention Graphs for Hallucination Detection cites this paper.
Neural Message-Passing on Attention Graphs for Hallucination Detection Discovering Latent Knowledge in Language Models Without Supervision
Reference 10
- Resolution
- unresolved
- no resolver link, observed 2026-08-04T13:52:07.804961Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 1d3ccaa2-bfbe-4d8b-b28e-3105ba86be42 · inbound
Geometry of Reason: Spectral Signatures of Valid Mathematical Reasoning cites this paper.
Geometry of Reason: Spectral Signatures of Valid Mathematical Reasoning Discovering Latent Knowledge in Language Models Without Supervision
Reference 2014
- Resolution
- unresolved
- no resolver link, observed 2026-08-03T13:03:21.532835Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 5b2de349-72c6-4f7b-ab80-61ce05f197a7 · inbound
No Reliable Evidence of Self-Reported Sentience in Small Large Language Models cites this paper.
No Reliable Evidence of Self-Reported Sentience in Small Large Language Models Discovering Latent Knowledge in Language Models Without Supervision
Reference 2024
- Resolution
- unresolved
- no resolver link, observed 2026-08-03T09:31:49.744774Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation fd69cf10-c629-4061-80ef-e2e15dd1ebc3 · inbound
TOPReward: Token Probabilities as Hidden Zero-Shot Rewards for Robotics cites this paper.
TOPReward: Token Probabilities as Hidden Zero-Shot Rewards for Robotics Discovering Latent Knowledge in Language Models Without Supervision
Reference 4
- Resolution
- unresolved
- no resolver link, observed 2026-08-02T21:43:07.066526Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation bded4634-bc39-47e4-84ff-415f09055973 · inbound
Emergent Manifold Separability during Reasoning in Large Language Models cites this paper.
Emergent Manifold Separability during Reasoning in Large Language Models Discovering Latent Knowledge in Language Models Without Supervision
Reference 3
- Resolution
- verified exact
- arxiv_id, observed 2026-05-15T20:34:08.372263Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 4aace6aa-ea9d-41de-b8b7-1bdd9cb7ca87 · inbound
Prompt Injection as Role Confusion cites this paper.
Prompt Injection as Role Confusion Discovering Latent Knowledge in Language Models Without Supervision
Reference 2024
- Resolution
- malformed identifier
- no resolver link, observed 2026-08-02T21:46:13.107901Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation d64fab97-26cc-4a83-84bc-4d05345c50ef · inbound
How do LLMs Compute Verbal Confidence cites this paper.
How do LLMs Compute Verbal Confidence Discovering Latent Knowledge in Language Models Without Supervision
Reference 3
- Resolution
- verified exact
- local_arxiv, observed 2026-05-21T10:40:00.611725Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 7be395c5-0fd1-4d93-a8ee-072d92950f40 · inbound
To See or To Please: Uncovering Visual Sycophancy and Split Beliefs in VLMs cites this paper.
To See or To Please: Uncovering Visual Sycophancy and Split Beliefs in VLMs Discovering Latent Knowledge in Language Models Without Supervision
Reference 5
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-15T20:34:08.372263Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 8b14138c-2eaf-4c4d-8303-afbd55836c96 · inbound
Interpretable Electrophysiological Features of Resting-State EEG Capture Cortical Network Dynamics in Parkinsons Disease cites this paper.
Interpretable Electrophysiological Features of Resting-State EEG Capture Cortical Network Dynamics in Parkinsons Disease Discovering Latent Knowledge in Language Models Without Supervision
Reference 4
- Resolution
- unresolved
- no resolver link, observed 2026-07-13T14:23:49.346727Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b2834ec8-8899-4835-81b0-70fbcf06de46 · inbound
Weakly Supervised Distillation of Hallucination Signals into Transformer Representations cites this paper.
Weakly Supervised Distillation of Hallucination Signals into Transformer Representations Discovering Latent Knowledge in Language Models Without Supervision
Reference 3
- Resolution
- verified exact
- arxiv_id, observed 2026-05-15T20:34:08.372263Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 5494bc89-f8f3-40da-974c-95101eb4dedd · inbound
The Long Delay to Arithmetic Generalization: When Learned Representations Outrun Behavior cites this paper.
The Long Delay to Arithmetic Generalization: When Learned Representations Outrun Behavior Discovering Latent Knowledge in Language Models Without Supervision
Reference 4
- Resolution
- verified exact
- arxiv_id, observed 2026-05-15T20:34:08.372263Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 13e3a36c-5c8b-49ba-9e03-63963fc621b9 · inbound
Learning Uncertainty from Sequential Internal Dispersion in Large Language Models cites this paper.
Learning Uncertainty from Sequential Internal Dispersion in Large Language Models Discovering Latent Knowledge in Language Models Without Supervision
Reference 3
- Resolution
- verified exact
- arxiv_id, observed 2026-05-15T20:34:08.372263Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 81c5f600-eaa4-4f86-b2a1-6cd0cd3819ec · inbound
How Tokenization Limits Phonological Knowledge Representation in Language Models and How to Improve Them cites this paper.
How Tokenization Limits Phonological Knowledge Representation in Language Models and How to Improve Them Discovering Latent Knowledge in Language Models Without Supervision
Reference 9
- Resolution
- verified exact
- arxiv_id, observed 2026-05-15T20:34:08.372263Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 794bba6f-e38f-49ce-99b6-7b1ae2127bba · inbound
Are LLM Uncertainty and Correctness Encoded by the Same Features? A Functional Dissociation via Sparse Autoencoders cites this paper.
Are LLM Uncertainty and Correctness Encoded by the Same Features? A Functional Dissociation via Sparse Autoencoders Discovering Latent Knowledge in Language Models Without Supervision
Reference 31
- Resolution
- verified exact
- arxiv_id, observed 2026-05-15T20:34:08.372263Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 20783210-ed4f-436e-a807-f47148b73a8c · inbound
How LLMs Detect and Correct Their Own Errors: The Role of Internal Confidence Signals cites this paper.
How LLMs Detect and Correct Their Own Errors: The Role of Internal Confidence Signals Discovering Latent Knowledge in Language Models Without Supervision
Reference 3
- Resolution
- verified exact
- arxiv_id, observed 2026-05-15T20:34:08.372263Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 51eddca8-d954-4d0a-92ae-a5689df686a0 · inbound
Perturbation Probing: A Two-Pass-per-Prompt Diagnostic for FFN Behavioral Circuits in Aligned LLMs cites this paper.
Perturbation Probing: A Two-Pass-per-Prompt Diagnostic for FFN Behavioral Circuits in Aligned LLMs Discovering Latent Knowledge in Language Models Without Supervision
Reference 5
- Resolution
- verified exact
- arxiv_id, observed 2026-05-15T20:34:08.372263Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation e77e8cdf-ab76-4031-8f23-5d13648ba686 · inbound
Geometric Deviation as an Unsupervised Pre-Generation Reliability Signal: Probing LLM Representations for Answerability cites this paper.
Geometric Deviation as an Unsupervised Pre-Generation Reliability Signal: Probing LLM Representations for Answerability Discovering Latent Knowledge in Language Models Without Supervision
Reference 7
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-15T20:34:08.372263Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation bf765001-42ef-4f78-92ff-c15d497f1ed4 · inbound
Decodable but Not Corrected by Fixed Residual-Stream Linear Steering: Evidence from Medical LLM Failure Regimes cites this paper.
Decodable but Not Corrected by Fixed Residual-Stream Linear Steering: Evidence from Medical LLM Failure Regimes Discovering Latent Knowledge in Language Models Without Supervision
Reference 10
- Resolution
- verified exact
- arxiv_id, observed 2026-05-15T20:34:08.372263Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 240a3d52-49f6-40e1-87b3-66b0bce81b0c · inbound
The Geometry of Forgetting: Temporal Knowledge Drift as an Independent Axis in LLM Representations cites this paper.
The Geometry of Forgetting: Temporal Knowledge Drift as an Independent Axis in LLM Representations Discovering Latent Knowledge in Language Models Without Supervision
Reference 6
- Resolution
- verified exact
- arxiv_id, observed 2026-05-15T20:34:08.372263Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 0be2a14b-9cd2-4eef-9ae3-3db49ac3544f · inbound
Repeated-Token Counting Reveals a Dissociation Between Representations and Outputs cites this paper.
Repeated-Token Counting Reveals a Dissociation Between Representations and Outputs Discovering Latent Knowledge in Language Models Without Supervision
Reference 1
- Resolution
- verified exact
- arxiv_id, observed 2026-05-15T20:34:08.372263Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 148004bd-cf73-4510-ae50-056f92d70652 · inbound
Repeated-Token Counting Reveals a Dissociation Between Representations and Outputs cites this paper.
Repeated-Token Counting Reveals a Dissociation Between Representations and Outputs Discovering Latent Knowledge in Language Models Without Supervision
Reference 2022
- Resolution
- unresolved
- no resolver link, observed 2026-08-02T14:31:12.034394Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 19837d01-1976-41dd-b6a2-05f2d0360a41 · inbound
LLM Agents Already Know When to Call Tools -- Even Without Reasoning cites this paper.
LLM Agents Already Know When to Call Tools -- Even Without Reasoning Discovering Latent Knowledge in Language Models Without Supervision
Reference 10
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-15T20:34:08.372263Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation b8e04aa4-4e78-48dc-ac11-00e62a8cd347 · inbound
LLM Agents Already Know When to Call Tools -- Even Without Reasoning cites this paper.
LLM Agents Already Know When to Call Tools -- Even Without Reasoning Discovering Latent Knowledge in Language Models Without Supervision
Reference 10
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-22T10:56:25.877372Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 0f003387-f22f-4da1-a30d-ae18832fadc6 · inbound
Positive Alignment: Artificial Intelligence for Human Flourishing cites this paper.
Positive Alignment: Artificial Intelligence for Human Flourishing Discovering Latent Knowledge in Language Models Without Supervision
Reference 169
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-15T20:34:08.372263Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 68f47cbd-83af-403b-9446-21e8ef19ac46 · inbound
Stories in Space: In-Context Learning Trajectories in Conceptual Belief Space cites this paper.
Stories in Space: In-Context Learning Trajectories in Conceptual Belief Space Discovering Latent Knowledge in Language Models Without Supervision
Reference 70
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-15T20:34:08.372263Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation d235f8c1-d6db-4105-b730-660c8b006b2c · inbound
Correcting Influence: Unboxing LLM Outputs with Orthogonal Latent Spaces cites this paper.
Correcting Influence: Unboxing LLM Outputs with Orthogonal Latent Spaces Discovering Latent Knowledge in Language Models Without Supervision
Reference 137
- Resolution
- verified exact
- arxiv_id, observed 2026-05-15T20:34:08.372263Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation f7b26cd2-f8f1-443c-bc01-60f5f5733347 · inbound
PAIR: Prefix-Aware Internal Reward Model for Multi-Turn Agent Optimization cites this paper.
PAIR: Prefix-Aware Internal Reward Model for Multi-Turn Agent Optimization Discovering Latent Knowledge in Language Models Without Supervision
Reference 1
- Resolution
- verified exact
- local_arxiv, observed 2026-05-20T10:43:12.459720Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation b12cf2a5-3e99-4956-ab39-40a3e91f015a · inbound
PAIR: Prefix-Aware Internal Reward Model for Multi-Turn Agent Optimization cites this paper.
PAIR: Prefix-Aware Internal Reward Model for Multi-Turn Agent Optimization Discovering Latent Knowledge in Language Models Without Supervision
Reference 1
- Resolution
- unresolved
- no resolver link, observed 2026-08-03T02:23:29.475276Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 8445a34d-820e-40ce-af87-ef1254df4472 · inbound
Trust or Abstain? A Self-Aware RAG Approach cites this paper.
Trust or Abstain? A Self-Aware RAG Approach Discovering Latent Knowledge in Language Models Without Supervision
Reference 4
- Resolution
- verified exact
- local_arxiv, observed 2026-05-20T23:03:50.377331Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation abc1a637-f32f-4bf0-965d-eb101dd82cdd · inbound
Manifold-Guided Attention Steering cites this paper.
Manifold-Guided Attention Steering Discovering Latent Knowledge in Language Models Without Supervision
Reference 2
- Resolution
- verified exact
- local_arxiv, observed 2026-05-22T09:14:45.318091Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 9a0d9cb4-ca11-4c2e-8336-fb1ffae02cef · inbound
Reading Calibrated Uncertainty from Language Model Trajectories cites this paper.
Reading Calibrated Uncertainty from Language Model Trajectories Discovering Latent Knowledge in Language Models Without Supervision
Reference 29
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-25T05:45:23.945287Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation ebe266b5-2bd6-4f20-bde9-98b6b079f2a8 · inbound
Detecting Is Not Resolving: The Monitoring Control Gap in Retrieval Augmented LLMs cites this paper.
Detecting Is Not Resolving: The Monitoring Control Gap in Retrieval Augmented LLMs Discovering Latent Knowledge in Language Models Without Supervision
Reference 18
- Resolution
- verified exact
- local_arxiv, observed 2026-06-29T17:13:44.850347Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation a37d5119-93fe-4af7-b9a2-f7cd5203f68c · inbound
Prefix-Safe Bayesian Belief Tracking for LLM Reasoning Reliability:Separating Calibration from Ranking cites this paper.
Prefix-Safe Bayesian Belief Tracking for LLM Reasoning Reliability:Separating Calibration from Ranking Discovering Latent Knowledge in Language Models Without Supervision
Reference 6
- Resolution
- verified exact
- local_arxiv, observed 2026-06-29T17:03:40.977377Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 0d5845af-5a7e-4218-8c30-489698a744e1 · inbound
The Attentional White Bear Effect in Transformer Language Models cites this paper.
The Attentional White Bear Effect in Transformer Language Models Discovering Latent Knowledge in Language Models Without Supervision
Reference 2
- Resolution
- verified exact
- local_arxiv, observed 2026-06-29T12:53:27.042291Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 425ad979-64c6-4b4e-bfec-1a9a76639028 · inbound
Can LLMs Use Linguistic Uncertainty Markers to Reliably Reflect Intrinsic Confidence? cites this paper.
Can LLMs Use Linguistic Uncertainty Markers to Reliably Reflect Intrinsic Confidence? Discovering Latent Knowledge in Language Models Without Supervision
Reference 7
- Resolution
- verified exact
- local_arxiv, observed 2026-06-29T12:23:24.421371Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation ea620236-5c89-40f9-9a39-07223841e287 · inbound
Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnet cites this paper.
Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnet Discovering Latent Knowledge in Language Models Without Supervision
Reference 12
- Resolution
- verified exact
- local_arxiv, observed 2026-06-29T07:53:13.424409Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 032fde70-6b90-4177-963a-7df421816826 · inbound
UniSteer: Text-Guided Flow Matching in Activation Space for Versatile LLM Steering cites this paper.
UniSteer: Text-Guided Flow Matching in Activation Space for Versatile LLM Steering Discovering Latent Knowledge in Language Models Without Supervision
Reference 3
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-06-29T08:13:15.611293Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 68d539dc-ec8c-445b-a156-a838d7880a14 · inbound
CANARY: Zero-Label Detection of Fine-Tuning Contamination in Language Models cites this paper.
CANARY: Zero-Label Detection of Fine-Tuning Contamination in Language Models Discovering Latent Knowledge in Language Models Without Supervision
Reference 4
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-07-01T22:26:18.041801Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation edcd55e5-5802-4b5e-8faa-c1aea132a358 · inbound
Hallucination Is Linearly Decodable from Mid-Layer Hidden States in Quantized LLMs cites this paper.
Hallucination Is Linearly Decodable from Mid-Layer Hidden States in Quantized LLMs Discovering Latent Knowledge in Language Models Without Supervision
Reference 3
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-06-28T19:22:34.868638Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 8c7a4ce7-7193-4630-ab35-d123cb01ad32 · inbound
Consistency Training Can Entrench Misalignment cites this paper.
Consistency Training Can Entrench Misalignment Discovering Latent Knowledge in Language Models Without Supervision
Reference 10
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-07-02T03:26:28.597517Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation b70fcb39-61c6-43c1-8e5a-8a6447d5c9fa · inbound
CASS-RTL: Correctness-Aware Subspace Steering for RTL Generation with LLMs cites this paper.
CASS-RTL: Correctness-Aware Subspace Steering for RTL Generation with LLMs Discovering Latent Knowledge in Language Models Without Supervision
Reference 30
- Resolution
- verified exact
- local_arxiv, observed 2026-07-02T15:57:07.351714Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 726e4a78-ae6f-4130-850d-d33cb3276854 · inbound
LLM Self-Recognition: Steering and Retrieving Activation Signatures cites this paper.
LLM Self-Recognition: Steering and Retrieving Activation Signatures Discovering Latent Knowledge in Language Models Without Supervision
Reference 26
- Resolution
- verified exact
- local_arxiv, observed 2026-06-28T01:41:29.292254Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation f1590fe2-9c58-4a74-80cb-8fb82e85583c · inbound
Adversarial Robustness of Activation Steering in Large Language Models cites this paper.
Adversarial Robustness of Activation Steering in Large Language Models Discovering Latent Knowledge in Language Models Without Supervision
Reference 15
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-07-02T16:37:09.415704Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation d2c0df88-dd3e-4fd3-a531-d1574f04206c · inbound
Now You (Still) See Me: Detecting Evasive Steganographic Payloads in LLMs cites this paper.
Now You (Still) See Me: Detecting Evasive Steganographic Payloads in LLMs Discovering Latent Knowledge in Language Models Without Supervision
Reference 32
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-07-03T02:07:33.628376Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 3fe7d966-cb83-4746-a98c-f67677d0a77f · inbound
PRISM: Recovering Instruction Sets from Language Model Activations cites this paper.
PRISM: Recovering Instruction Sets from Language Model Activations Discovering Latent Knowledge in Language Models Without Supervision
Reference 8
- Resolution
- verified exact
- local_arxiv, observed 2026-06-27T17:01:08.112795Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation d2db5217-5ae7-4d8a-98da-78e0d5e50ee5 · inbound
Toward Calibrated, Fair, and accurate Deepfake Detection cites this paper.
Toward Calibrated, Fair, and accurate Deepfake Detection Discovering Latent Knowledge in Language Models Without Supervision
Reference 61
- Resolution
- verified exact
- local_arxiv, observed 2026-06-28T07:11:45.306077Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 29b05033-4b28-41f9-8174-14e58829eee9 · inbound
Forecasting Future Behavior as a Learning Task cites this paper.
Forecasting Future Behavior as a Learning Task Discovering Latent Knowledge in Language Models Without Supervision
Reference 59
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-07-03T06:07:41.329043Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation f33b6223-44aa-466e-92ca-5aa5c8c7b925 · inbound
Pre-Generation Hallucination Detection in Large Language Models via Soft-Target Attention Probing cites this paper.
Pre-Generation Hallucination Detection in Large Language Models via Soft-Target Attention Probing Discovering Latent Knowledge in Language Models Without Supervision
Reference 4
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-07-04T07:59:40.433972Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 7f67689c-c851-4bea-ab5b-dab52f299521 · inbound
When Agents Commit Too Soon: Diagnosing Premature Commitment in LLM Agents cites this paper.
When Agents Commit Too Soon: Diagnosing Premature Commitment in LLM Agents Discovering Latent Knowledge in Language Models Without Supervision
Reference 4
- Resolution
- verified exact
- local_arxiv, observed 2026-07-04T10:49:45.709560Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation a6bb1225-a0a3-4c8e-a376-655bf79aa0e8 · inbound
Plans Don't Persist: Why Context Management Is Load Bearing for LLM Agents cites this paper.
Plans Don't Persist: Why Context Management Is Load Bearing for LLM Agents Discovering Latent Knowledge in Language Models Without Supervision
Reference 2
- Resolution
- verified exact
- local_arxiv, observed 2026-07-04T10:49:46.382030Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 1cdbb5a5-2feb-45cb-8bf8-99aafe702d90 · inbound
Perfect Detection, Failed Control: The Geometry of Knowing vs. Steering in Language Models cites this paper.
Perfect Detection, Failed Control: The Geometry of Knowing vs. Steering in Language Models Discovering Latent Knowledge in Language Models Without Supervision
Reference 3
- Resolution
- verified exact
- local_arxiv, observed 2026-07-04T16:49:57.477292Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 0cfb732d-67cc-4985-a2fc-187b0d3880c8 · inbound
Radical AI Interpretability cites this paper.
Radical AI Interpretability Discovering Latent Knowledge in Language Models Without Supervision
Reference 29
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-07-04T13:09:51.066147Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 815fb3b0-c0b6-4a99-afab-60022749c5a6 · inbound
Auditing Framing-Sensitive Behavioral Instability in Large Language Models for Mental Health Interactions cites this paper.
Auditing Framing-Sensitive Behavioral Instability in Large Language Models for Mental Health Interactions Discovering Latent Knowledge in Language Models Without Supervision
Reference 6
- Resolution
- verified exact
- local_arxiv, observed 2026-07-04T14:09:52.856519Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 9c8c957e-203c-4a69-89b5-636ecf12beba · inbound
From Signals to Transfer: A Factorised Study of Probe-Based Uncertainty Estimation in Large Language Models cites this paper.
From Signals to Transfer: A Factorised Study of Probe-Based Uncertainty Estimation in Large Language Models Discovering Latent Knowledge in Language Models Without Supervision
Reference 8
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-06-29T18:23:51.030162Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 988d2075-4bd9-45aa-902e-1ed74210f20c · inbound
The strength of clinical evidence is recoverable from language model representations but not from their stated grades cites this paper.
The strength of clinical evidence is recoverable from language model representations but not from their stated grades Discovering Latent Knowledge in Language Models Without Supervision
Reference 12
- Resolution
- verified exact
- local_arxiv, observed 2026-06-30T09:34:34.612813Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation b3528d69-d2c3-49fb-8a45-7bc3bad167a1 · inbound
Internal-State Probes Read the Situation, Not the Action: Three Negative Results for Pre-Action Misalignment Monitoring cites this paper.
Internal-State Probes Read the Situation, Not the Action: Three Negative Results for Pre-Action Misalignment Monitoring Discovering Latent Knowledge in Language Models Without Supervision
Reference 13
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-06-30T07:44:22.026858Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 51c3f320-af26-410a-b377-1e688649833e · inbound
Reinforcement Learning with Metacognitive Feedback Elicits Faithful Uncertainty Expression in LLMs cites this paper.
Reinforcement Learning with Metacognitive Feedback Elicits Faithful Uncertainty Expression in LLMs Discovering Latent Knowledge in Language Models Without Supervision
Reference 9
- Resolution
- verified exact
- local_arxiv, observed 2026-07-01T10:35:42.045762Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 65575cb8-6020-4fc1-b1c3-ec9f82a82757 · inbound
PRA-RAG: Provably Robust Aggregation in Retrieval-Augmented Generation against Retrieval Corruption cites this paper.
PRA-RAG: Provably Robust Aggregation in Retrieval-Augmented Generation against Retrieval Corruption Discovering Latent Knowledge in Language Models Without Supervision
Reference 60
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-07-02T23:47:27.197660Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation ac1e7194-fc01-4a14-bd82-fbc71b4e4c05 · inbound
Readable but Not Controllable: Neuron-Level Evidence for Medical LLM Hallucination cites this paper.
Readable but Not Controllable: Neuron-Level Evidence for Medical LLM Hallucination Discovering Latent Knowledge in Language Models Without Supervision
Reference 3
- Resolution
- verified exact
- local_arxiv, observed 2026-07-02T19:17:17.626552Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation e99762da-d12e-4ea4-b327-88f774e91423 · inbound
Subliminal Clocks: Latent Time Modelling in Diffusion Language Models cites this paper.
Subliminal Clocks: Latent Time Modelling in Diffusion Language Models Discovering Latent Knowledge in Language Models Without Supervision
Reference 22
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-07-03T13:58:21.254599Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation cc5b659a-cfca-421e-948d-a9b4b4bd793c · inbound
Subliminal Clocks: Latent Time Modelling in Diffusion Language Models cites this paper.
Subliminal Clocks: Latent Time Modelling in Diffusion Language Models Discovering Latent Knowledge in Language Models Without Supervision
Reference 22
- Resolution
- unresolved
- no resolver link, observed 2026-08-02T09:07:02.234749Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation fdb5c000-5b4c-40a3-b989-4f544d912bc1 · inbound
Weak-to-Strong Generalization via Direct On-Policy Distillation cites this paper.
Weak-to-Strong Generalization via Direct On-Policy Distillation Discovering Latent Knowledge in Language Models Without Supervision
Reference 89
- Resolution
- verified exact
- local_arxiv, observed 2026-07-07T12:33:45.027092Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 5ddb4ac6-1bdc-4ba8-918d-16f06d406da1 · inbound
Weak-to-Strong Generalization via Direct On-Policy Distillation cites this paper.
Weak-to-Strong Generalization via Direct On-Policy Distillation Discovering Latent Knowledge in Language Models Without Supervision
Reference 85
- Resolution
- unresolved
- no resolver link, observed 2026-07-11T07:01:56.628017Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 74b1ff89-6bd2-4fc3-9ea7-260b4678a84c · inbound
Dissociating the Internal Representations of Sycophancy in LLMs cites this paper.
Dissociating the Internal Representations of Sycophancy in LLMs Discovering Latent Knowledge in Language Models Without Supervision
Reference 3
- Resolution
- verified exact
- local_arxiv, observed 2026-07-09T22:06:35.316057Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 9bbff01e-d216-4a27-9234-b4bd2691c602 · inbound
Dissociating the Internal Representations of Sycophancy in LLMs cites this paper.
Dissociating the Internal Representations of Sycophancy in LLMs Discovering Latent Knowledge in Language Models Without Supervision
Reference 2022
- Resolution
- unresolved
- no resolver link, observed 2026-08-02T08:11:39.080789Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation ef966a6b-d11d-4927-a5ff-07acb8c4ad06 · inbound
Prompt Compression via Activation Aggregation cites this paper.
Prompt Compression via Activation Aggregation Discovering Latent Knowledge in Language Models Without Supervision
Reference 25
- Resolution
- verified exact
- local_arxiv, observed 2026-07-10T08:06:57.502233Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 2d105eec-e4fb-4170-aeb5-ce3b335bcbf2 · inbound
Exposure is not manifestation: measurement target and output resolution jointly determine which behavioural-faithfulness evaluator wins cites this paper.
Exposure is not manifestation: measurement target and output resolution jointly determine which behavioural-faithfulness evaluator wins Discovering Latent Knowledge in Language Models Without Supervision
Reference 39
- Resolution
- unresolved
- no resolver link, observed 2026-08-02T07:44:06.996445Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 153b3803-5472-4faf-b276-4b1bb31ccf6d · inbound
The Count Is There, but Misaligned: Understanding and Correcting Counting Failures in VLMs cites this paper.
The Count Is There, but Misaligned: Understanding and Correcting Counting Failures in VLMs Discovering Latent Knowledge in Language Models Without Supervision
Reference 41
- Resolution
- unresolved
- no resolver link, observed 2026-07-13T02:15:42.731438Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 19d968ca-3e05-41c8-a177-2d7064d74d55 · inbound
Confidently Wrong: Detecting Hallucinations in Financial Question Answering from LLM Internal States cites this paper.
Confidently Wrong: Detecting Hallucinations in Financial Question Answering from LLM Internal States Discovering Latent Knowledge in Language Models Without Supervision
Reference 5
- Resolution
- unresolved
- no resolver link, observed 2026-07-14T05:45:08.896651Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 029b3bbe-157e-4230-9e2a-02fd015bb33e · inbound
Inside the Unfair Judge: A Mechanistic Interpretability Account of LLM-as-Judge Bias cites this paper.
Inside the Unfair Judge: A Mechanistic Interpretability Account of LLM-as-Judge Bias Discovering Latent Knowledge in Language Models Without Supervision
Reference 49
- Resolution
- unresolved
- no resolver link, observed 2026-07-14T02:33:34.084111Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation e0d54499-1682-4ac0-92b3-a092556fbc40 · inbound
The Computational Basis of Confidence in Large Language Models cites this paper.
The Computational Basis of Confidence in Large Language Models Discovering Latent Knowledge in Language Models Without Supervision
Reference 13
- Resolution
- unresolved
- no resolver link, observed 2026-08-02T06:37:40.498943Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation fc4cf203-9333-48e0-bd82-110f326d7d03 · inbound
The Refusal Residue: When Probes Catch Alignment Faking and When They Don't cites this paper.
The Refusal Residue: When Probes Catch Alignment Faking and When They Don't Discovering Latent Knowledge in Language Models Without Supervision
Reference 13
- Resolution
- unresolved
- no resolver link, observed 2026-08-02T05:33:17.045238Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation d5d3e08a-91a9-4b84-a73b-1f135effb8c3 · inbound
Graded Entity-Familiarity Readouts in Language Models: Polish Adaptation, Cross-Language Robustness, and Refusal Steering cites this paper.
Graded Entity-Familiarity Readouts in Language Models: Polish Adaptation, Cross-Language Robustness, and Refusal Steering Discovering Latent Knowledge in Language Models Without Supervision
Reference 59
- Resolution
- unresolved
- no resolver link, observed 2026-08-02T04:52:45.338836Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 6ddf48a2-c533-4b2d-accc-03a15f001caa · inbound
Multi-Head Latent Control: A Unified Interface for LLM Agent Decision Making cites this paper.
Multi-Head Latent Control: A Unified Interface for LLM Agent Decision Making Discovering Latent Knowledge in Language Models Without Supervision
Reference 3
- Resolution
- unresolved
- no resolver link, observed 2026-08-02T02:42:01.203968Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 2bcafe71-c745-4368-8b24-f0556c70d460 · inbound
The Anatomy of a Truth Direction: Knowledge-Dependent Dimensionality, a Relational Law, and a Convergent Category Geometry in Small Language Models cites this paper.
The Anatomy of a Truth Direction: Knowledge-Dependent Dimensionality, a Relational Law, and a Convergent Category Geometry in Small Language Models Discovering Latent Knowledge in Language Models Without Supervision
Reference 1
- Resolution
- unresolved
- no resolver link, observed 2026-08-01T20:09:48.551226Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation fca63d1e-16b8-453c-8966-7f98fb4a1a71 · inbound
Logical Judgments Under Pressure: Diagnosing Syllogistic Stability with Learned Soft Prefixes cites this paper.
Logical Judgments Under Pressure: Diagnosing Syllogistic Stability with Learned Soft Prefixes Discovering Latent Knowledge in Language Models Without Supervision
Reference 4
- Resolution
- unresolved
- no resolver link, observed 2026-08-01T15:40:35.398243Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 31fcd1be-d249-4209-9f92-08c7bd29507f · inbound
Reading and Steering Representations of Materials-Science Mechanisms in an Open-Weight Language Model cites this paper.
Reading and Steering Representations of Materials-Science Mechanisms in an Open-Weight Language Model Discovering Latent Knowledge in Language Models Without Supervision
Reference 39
- Resolution
- unresolved
- no resolver link, observed 2026-08-01T10:59:55.337046Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation bac76bc1-07cc-4137-a403-25d788855de2 · inbound
Securing Multimodal AI through Internal Information Decomposition cites this paper.
Securing Multimodal AI through Internal Information Decomposition Discovering Latent Knowledge in Language Models Without Supervision
Reference 2024
- Resolution
- unresolved
- no resolver link, observed 2026-08-02T15:02:58.141704Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.