Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-05-08T12:30:51.094216Z
Paper Citation Record · LEDGER
How LLMs Detect and Correct Their Own Errors: The Role of Internal Confidence Signals
As of 5 August 2026, this Paper Citation Record lists 35 of 35 outbound references and 2 inbound Pith citation observations for arXiv:2604.22271.
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 2026-08-05T06:32:48.257954+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links, observed 2026-08-01T19:59:11.740772Z
A source-named dated measurement, never combined with another source.
Source: pith, observed 2026-08-05T02:28:24.338817Z
Reference resolution
35 of 35 outbound references displayed
- verified exact24
- verified fuzzy7
- unresolved0
- parse uncertain0
- malformed identifier0
- metadata mismatch4
External citation measurements
0
pith, observed 2026-08-05T02:28:24.338817Z
Outbound references
Observation 9b25bb24-354a-4658-9610-2ca325bcbef9 · outbound
This paper cites The Internal State of an LLM Knows When It's Lying.
How LLMs Detect and Correct Their Own Errors: The Role of Internal Confidence Signals The Internal State of an LLM Knows When It's Lying
Reference 1
- Resolution
- verified exact
- arxiv_id, observed 2026-05-16T00:08:36.671090Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 5030ba2f-b66d-46a8-9596-3dd811c441e9 · outbound
This paper cites The validation gap: A mechanistic analysis of how language models compute arithmetic but fail to validate it.
How LLMs Detect and Correct Their Own Errors: The Role of Internal Confidence Signals The validation gap: A mechanistic analysis of how language models compute arithmetic but fail to validate it
Reference 2
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-26T13:17:48.402329Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 20783210-ed4f-436e-a807-f47148b73a8c · outbound
This paper cites Discovering Latent Knowledge in Language Models Without Supervision.
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 2026-08-05T06:32:48.257954+00:00.
Observation e43b8788-a9de-4ca4-b935-f563d28f1586 · outbound
This paper cites Sets: Leveraging self-verification and self-correction for improved test-time scaling.
How LLMs Detect and Correct Their Own Errors: The Role of Internal Confidence Signals Sets: Leveraging self-verification and self-correction for improved test-time scaling
Reference 4
- Resolution
- verified exact
- arxiv_id, observed 2026-05-11T19:16:06.866730Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation e7f9b55c-5e93-429e-9c8b-0be8ad9ce277 · outbound
This paper cites Cognitive Behaviors that Enable Self-Improving Reasoners, or, Four Habits of Highly Effective STaRs.
How LLMs Detect and Correct Their Own Errors: The Role of Internal Confidence Signals Cognitive Behaviors that Enable Self-Improving Reasoners, or, Four Habits of Highly Effective STaRs
Reference 5
- Resolution
- verified exact
- arxiv_id, observed 2026-05-17T11:40:33.380427Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 821ccce8-7463-41bb-b7f3-7ad2508142b3 · outbound
This paper cites A Survey of Confidence Estimation and Calibration in Large Language Models.
How LLMs Detect and Correct Their Own Errors: The Role of Internal Confidence Signals A Survey of Confidence Estimation and Calibration in Large Language Models
Reference 6
- Resolution
- verified exact
- arxiv_id, observed 2026-05-11T19:16:06.961898Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation d42eac41-9ee6-4070-808c-79f93763e36e · outbound
This paper cites How to use and interpret activation patching.
How LLMs Detect and Correct Their Own Errors: The Role of Internal Confidence Signals How to use and interpret activation patching
Reference 7
- Resolution
- verified exact
- arxiv_id, observed 2026-05-16T20:34:07.011585Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation e1f72d2e-359e-4a81-90d4-2d4fb433be96 · outbound
This paper cites arXiv preprint arXiv:2510.20487 , year =.
How LLMs Detect and Correct Their Own Errors: The Role of Internal Confidence Signals arXiv preprint arXiv:2510.20487 , year =
Reference 8
- Resolution
- verified exact
- arxiv_id, observed 2026-05-11T19:16:06.929215Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 2ecb92e1-547f-4065-85a5-3e82b12f6f20 · outbound
This paper cites TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension.
How LLMs Detect and Correct Their Own Errors: The Role of Internal Confidence Signals TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension
Reference 9
- Resolution
- verified exact
- local_arxiv, observed 2026-05-11T19:16:07.019909Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 8dc26070-da47-41f8-8e9a-8ab8f1af48a1 · outbound
This paper cites Language Models (Mostly) Know What They Know.
How LLMs Detect and Correct Their Own Errors: The Role of Internal Confidence Signals Language Models (Mostly) Know What They Know
Reference 10
- Resolution
- verified exact
- local_arxiv, observed 2026-05-11T19:16:07.004691Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 1ba2f18b-f0fa-4d29-9862-6f8c88201457 · outbound
This paper cites How do LLMs Compute Verbal Confidence.
How LLMs Detect and Correct Their Own Errors: The Role of Internal Confidence Signals How do LLMs Compute Verbal Confidence
Reference 11
- Resolution
- verified exact
- arxiv_id, observed 2026-05-20T02:04:53.698588Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 1e3bd625-9049-4cd4-a4ee-379fb47e627b · outbound
This paper cites Confidence Matters: Revisiting Intrinsic Self-Correction Capabilities of Large Language Models.
How LLMs Detect and Correct Their Own Errors: The Role of Internal Confidence Signals Confidence Matters: Revisiting Intrinsic Self-Correction Capabilities of Large Language Models
Reference 12
- Resolution
- verified exact
- arxiv_id, observed 2026-05-11T19:16:06.907479Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 9980e0e0-82e5-4552-bfc5-0cc584812086 · outbound
This paper cites Large Language Models have Intrinsic Self-Correction Ability.
How LLMs Detect and Correct Their Own Errors: The Role of Internal Confidence Signals Large Language Models have Intrinsic Self-Correction Ability
Reference 13
- Resolution
- verified exact
- arxiv_id, observed 2026-05-11T19:16:06.914274Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation d4c75156-e4d3-445a-b061-f949c8f73cc3 · outbound
This paper cites Liu, J., Jain, J., Diab, M., and Subramani, N.
How LLMs Detect and Correct Their Own Errors: The Role of Internal Confidence Signals Liu, J., Jain, J., Diab, M., and Subramani, N
Reference 14
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-11T19:16:06.999169Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 534693cc-b836-48db-a685-48178f0bf927 · outbound
This paper cites Monte MacDiarmid, Timothy Maxwell, Nicholas Schiefer, Jesse Mu, Jared Kaplan, David Duvenaud, Samuel R.
How LLMs Detect and Correct Their Own Errors: The Role of Internal Confidence Signals Monte MacDiarmid, Timothy Maxwell, Nicholas Schiefer, Jesse Mu, Jared Kaplan, David Duvenaud, Samuel R
Reference 15
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-11T19:16:06.986725Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation b0b9c4a5-46af-43b6-85b2-1bfd588932d8 · outbound
This paper cites LLMs Know More Than They Show: On the Intrinsic Representation of LLM Hallucinations.
How LLMs Detect and Correct Their Own Errors: The Role of Internal Confidence Signals LLMs Know More Than They Show: On the Intrinsic Representation of LLM Hallucinations
Reference 16
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-11T19:16:06.900670Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation b6047ae1-49f3-45b1-8180-8e12274e355c · outbound
This paper cites Steering Llama 2 via Contrastive Activation Addition.
How LLMs Detect and Correct Their Own Errors: The Role of Internal Confidence Signals Steering Llama 2 via Contrastive Activation Addition
Reference 17
- Resolution
- verified exact
- arxiv_id, observed 2026-05-11T20:37:21.847050Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation a813e620-4077-4b11-b988-810bb5d5c566 · outbound
This paper cites Mark Steyvers, Heliodoro Tejeda, Aakriti Kumar, Catarina Bel´em, Sheer Karny, Xinyue Hu, Lukas W.
How LLMs Detect and Correct Their Own Errors: The Role of Internal Confidence Signals Mark Steyvers, Heliodoro Tejeda, Aakriti Kumar, Catarina Bel´em, Sheer Karny, Xinyue Hu, Lukas W
Reference 18
- Resolution
- verified exact
- doi, observed 2026-05-08T12:34:59.025100Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation b6cf15a7-8050-466e-b16a-50825f8e06b2 · outbound
This paper cites Improving Instruction-Following in Language Models through Activation Steering.
How LLMs Detect and Correct Their Own Errors: The Role of Internal Confidence Signals Improving Instruction-Following in Language Models through Activation Steering
Reference 19
- Resolution
- verified exact
- arxiv_id, observed 2026-05-11T19:16:06.848179Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation bf5f9c59-2590-4fb3-a9fe-939cc455157e · outbound
This paper cites Gemma 3 Technical Report.
How LLMs Detect and Correct Their Own Errors: The Role of Internal Confidence Signals Gemma 3 Technical Report
Reference 20
- Resolution
- verified exact
- local_arxiv, observed 2026-05-11T19:16:06.993174Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 8113b983-2179-454c-896e-cce94e929d75 · outbound
This paper cites Just Ask for Calibration: Strategies for Eliciting Calibrated Confidence Scores from Language Models Fine-Tuned with Human Feedback.
How LLMs Detect and Correct Their Own Errors: The Role of Internal Confidence Signals Just Ask for Calibration: Strategies for Eliciting Calibrated Confidence Scores from Language Models Fine-Tuned with Human Feedback
Reference 21
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-11T19:16:06.940805Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation f7053478-687f-4e3e-9ce3-c5596cdaec71 · outbound
This paper cites Steering Language Models With Activation Engineering.
How LLMs Detect and Correct Their Own Errors: The Role of Internal Confidence Signals Steering Language Models With Activation Engineering
Reference 22
- Resolution
- verified exact
- local_arxiv, observed 2026-05-11T19:16:06.852935Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 7cc2956a-a5c8-4a4d-821c-3d138f211e59 · outbound
This paper cites Base Models Know How to Reason, Thinking Models Learn When.
How LLMs Detect and Correct Their Own Errors: The Role of Internal Confidence Signals Base Models Know How to Reason, Thinking Models Learn When
Reference 23
- Resolution
- verified exact
- arxiv_id, observed 2026-07-08T02:18:39.926237Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 941f5e68-792c-4568-ba71-b24b273bf530 · outbound
This paper cites Reasoning-Finetuning Repurposes Latent Representations in Base Models.
How LLMs Detect and Correct Their Own Errors: The Role of Internal Confidence Signals Reasoning-Finetuning Repurposes Latent Representations in Base Models
Reference 24
- Resolution
- verified exact
- arxiv_id, observed 2026-05-11T19:16:06.925057Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 42c1e059-f4eb-4d69-8b7d-e1b9485ce0f9 · outbound
This paper cites Large language models are better reasoners with self-verification.
How LLMs Detect and Correct Their Own Errors: The Role of Internal Confidence Signals Large language models are better reasoners with self-verification
Reference 25
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-26T13:17:48.383050Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 3cb35885-4dd2-49e1-99ad-7a8ca21a32e2 · outbound
This paper cites A broad-coverage challenge corpus for sentence understanding through inference.
How LLMs Detect and Correct Their Own Errors: The Role of Internal Confidence Signals A broad-coverage challenge corpus for sentence understanding through inference
Reference 26
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-26T13:17:48.395982Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation eb2ab648-8db5-49a3-ab25-bbb6b92e56b7 · outbound
This paper cites Know when you’re wrong: Aligning confidence with correctness for LLM error detection.arXiv preprint arXiv:2603.06604.
How LLMs Detect and Correct Their Own Errors: The Role of Internal Confidence Signals Know when you’re wrong: Aligning confidence with correctness for LLM error detection.arXiv preprint arXiv:2603.06604
Reference 27
- Resolution
- verified exact
- arxiv_id, observed 2026-05-11T19:16:06.879397Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation e9a4594c-8fc0-40e3-8f9c-4e21dc1fab29 · outbound
This paper cites Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs.
How LLMs Detect and Correct Their Own Errors: The Role of Internal Confidence Signals Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs
Reference 28
- Resolution
- verified exact
- arxiv_id, observed 2026-05-13T08:40:32.974213Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 3834b0e4-2513-40eb-a978-fef8442e08bd · outbound
This paper cites Step Back to Leap Forward: Self-Backtracking for Boosting Reasoning of Language Models.
How LLMs Detect and Correct Their Own Errors: The Role of Internal Confidence Signals Step Back to Leap Forward: Self-Backtracking for Boosting Reasoning of Language Models
Reference 29
- Resolution
- verified exact
- arxiv_id, observed 2026-05-11T19:16:06.974960Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 32ec44d1-6301-4eed-a902-62d6985ba020 · outbound
This paper cites Dongryeol Yoon, Seongyun Kim, Sukyung Yang, Seongjin Kim, Yireun Kim, Eunji Kim, Eunsol Choi, Yohan Kim, and Minjoon Seo.
How LLMs Detect and Correct Their Own Errors: The Role of Internal Confidence Signals Dongryeol Yoon, Seongyun Kim, Sukyung Yang, Seongjin Kim, Yireun Kim, Eunji Kim, Eunsol Choi, Yohan Kim, and Minjoon Seo
Reference 30
- Resolution
- verified exact
- doi, observed 2026-05-08T12:34:59.023062Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 962167b0-6575-47b2-88b5-ae7033b700bf · outbound
This paper cites Towards Best Practices of Activation Patching in Language Models: Metrics and Methods.
How LLMs Detect and Correct Their Own Errors: The Role of Internal Confidence Signals Towards Best Practices of Activation Patching in Language Models: Metrics and Methods
Reference 31
- Resolution
- verified exact
- arxiv_id, observed 2026-05-17T11:56:11.458226Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation e28a3b56-0f6f-4fef-8100-e8bcd0bdd24a · outbound
This paper cites No chance.
How LLMs Detect and Correct Their Own Errors: The Role of Internal Confidence Signals No chance
Reference 32
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-26T13:17:48.390313Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation a21256e0-0cbb-48df-833a-f3d536854f87 · outbound
This paper cites (2024); Chen et al.
How LLMs Detect and Correct Their Own Errors: The Role of Internal Confidence Signals (2024); Chen et al
Reference 33
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-26T13:17:48.370724Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 68540711-125d-4c3f-be9b-ecea4c63a3e1 · outbound
This paper cites consistency heads.
How LLMs Detect and Correct Their Own Errors: The Role of Internal Confidence Signals consistency heads
Reference 34
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-26T13:17:48.378105Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 52c3eabc-8b40-4644-b96c-7b2d6828cb3c · outbound
This paper cites the candidate’s answer.
How LLMs Detect and Correct Their Own Errors: The Role of Internal Confidence Signals the candidate’s answer
Reference 35
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-26T13:17:48.374585Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Pith citing papers
Observation ec7c6509-430e-4217-b21b-499937208c35 · inbound
Hypothesis generation and updating in large language models cites this paper.
Hypothesis generation and updating in large language models How LLMs Detect and Correct Their Own Errors: The Role of Internal Confidence Signals
Reference 13
- Resolution
- verified exact
- local_arxiv, observed 2026-05-08T21:14:12.052674Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 55f25a3a-6841-45be-b006-c53636a7cf37 · inbound
Diagnosing Correctness Probes under Self-Judgement Confounding cites this paper.
Diagnosing Correctness Probes under Self-Judgement Confounding How LLMs Detect and Correct Their Own Errors: The Role of Internal Confidence Signals
Reference 27
- Resolution
- unresolved
- no resolver link, observed 2026-08-01T19:59:11.740772Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.