Pith. sign in

Paper Citation Record · LEDGER

In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering

As of 20 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 45 inbound Pith citation observations for arXiv:2311.06668.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2311.06668 v3

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 45 of 45 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-19T06:32:44.657259+00:00

measured 45 of 45 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-16T05:55:21.232172Z

measured 1 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: pith, observed 2026-08-05T02:28:24.338817Z

Reference resolution

0 of 0 outbound references displayed

  • verified exact0
  • verified fuzzy0
  • unresolved0
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

4
pith, observed 2026-08-05T02:28:24.338817Z

Outbound references

No outbound reference observations are available for this paper version.

Pith citing papers

Observation 2fcd56de-01be-4057-9f95-0c8ddbcf153a · inbound

Steering Language Models With Activation Engineering cites this paper.

Steering Language Models With Activation Engineering In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering

Reference 85

Resolution
verified exact
arxiv_id, observed 2026-05-11T00:14:14.836549Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=arxiv_source observed=2026-05-11T00:14:14.079351Z digest=sha256:01dfe2de84e700a2382778630e37593f64e142474b97f73be28ba1dd04919678

Observation e38341a5-033f-448e-8c55-51ed8720aec8 · inbound

Steering Llama 2 via Contrastive Activation Addition cites this paper.

Steering Llama 2 via Contrastive Activation Addition In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering

Reference 10

Resolution
verified exact
arxiv_id, observed 2026-05-11T20:37:21.305134Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=arxiv_source observed=2026-05-11T20:37:20.408376Z digest=sha256:da08d8389c776d9177d71eadb558cfc1255e6ff524ab28dc2eeb5df5b42e2fff

Observation ec9e69e6-7462-4872-b81b-c07493e66d53 · inbound

Can sparse autoencoders be used to decompose and interpret steering vectors? cites this paper.

Can sparse autoencoders be used to decompose and interpret steering vectors? In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering

Reference 10

Resolution
unresolved
no resolver link, observed 2026-08-12T21:26:42.212109Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T21:26:42.212109Z digest=sha256:0dfa3009084a7e86fede9c3114afe00daae1d4cb727f399013d7ad146cc70d15

Observation e7718e7c-9842-4d2b-bed2-04add62bab21 · inbound

Steering Language Model Refusal with Sparse Autoencoders cites this paper.

Steering Language Model Refusal with Sparse Autoencoders In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering

Reference 39

Resolution
unresolved
no resolver link, observed 2026-08-12T18:45:48.511514Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T18:45:48.511514Z digest=sha256:85082e92b701b2e65d27279d6d427f3b2ce7606e2971d98a7eec47f39a5d516e

Observation edfe781f-5283-43f7-8127-8e5d2e6c7c74 · inbound

Task Vectors in In-Context Learning: Emergence, Formation, and Benefit cites this paper.

Task Vectors in In-Context Learning: Emergence, Formation, and Benefit In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering

Reference 25

Resolution
unresolved
no resolver link, observed 2026-08-10T20:15:28.337375Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-10T20:15:28.337375Z digest=sha256:c18c4738f42c3df0d9b8f5fa91ef077914bd6e2c2a64fe91abf0fdb060a089e1

Observation 9b6cf97a-2567-4702-b105-087a6e35b8af · inbound

Mechanistic Understandings of Representation Vulnerabilities and Engineering Robust Vision Transformers cites this paper.

Mechanistic Understandings of Representation Vulnerabilities and Engineering Robust Vision Transformers In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering

Reference 47

Resolution
unresolved
no resolver link, observed 2026-08-08T21:55:56.879587Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-08T21:55:56.879587Z digest=sha256:dbe5618efedfd9bb2a5938ebf0b9bf9c01151f548ba653b5c29f2aa336ed7f37

Observation 1fdc9b0e-ce03-4ee8-9131-5af2b5af733c · inbound

Task-driven Layerwise Additive Activation Intervention cites this paper.

Task-driven Layerwise Additive Activation Intervention In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering

Reference 13

Resolution
unresolved
no resolver link, observed 2026-08-08T16:46:58.469327Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-08T16:46:58.469327Z digest=sha256:e9e4ee93b7ca0ddc6c8d08e6f61899f7fe9e74d1cf7a8211be0e4445011a83d4

Observation 4a3f9dc7-fcbf-4836-ad92-a0d8918cb3ce · inbound

CODI: Compressing Chain-of-Thought into Continuous Space via Self-Distillation cites this paper.

CODI: Compressing Chain-of-Thought into Continuous Space via Self-Distillation In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering

Reference 111

Resolution
verified exact
arxiv_id, observed 2026-05-17T23:14:57.656058Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=arxiv_source observed=2026-05-17T23:14:57.501341Z digest=sha256:505b44b857d3a8399f7bd5623a5326ccf2b1a09b3b1e018b883ca4a84a6975c9

Observation 0d634f99-50b8-40a2-823f-02943306e301 · inbound

Improving Reasoning Performance in Large Language Models via Representation Engineering cites this paper.

Improving Reasoning Performance in Large Language Models via Representation Engineering In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering

Reference 10

Resolution
unresolved
no resolver link, observed 2026-08-16T05:55:21.232172Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T05:55:21.232172Z digest=sha256:aa81b77e6b8e85dcafa198b44f1764a4606c0682f05919174f5cc96df35abd6c

Observation e6aee399-47a2-4221-90da-cf60498f4283 · inbound

Denoising Concept Vectors with Sparse Autoencoders for Improved Language Model Steering cites this paper.

Denoising Concept Vectors with Sparse Autoencoders for Improved Language Model Steering In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering

Reference 15

Resolution
unresolved
no resolver link, observed 2026-08-07T15:30:21.522969Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T15:30:21.522969Z digest=sha256:0c117c6bc80a25fac304ca9cf503734dd77070ff1a916b9c05f988173e6e7d72

Observation 5e1b10ee-a5f8-4450-a04b-24747fec5c46 · inbound

Sparse Activation Editing for Reliable Instruction Following in Narratives cites this paper.

Sparse Activation Editing for Reliable Instruction Following in Narratives In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering

Reference 19

Resolution
unresolved
no resolver link, observed 2026-08-07T15:04:54.953508Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T15:04:54.953508Z digest=sha256:f43ad8eb358b66a4555c690e4d08a7d853e119e8d031110fb3a893a9a69776bc

Observation 230253f7-1030-4595-8aa5-ef821a7fa717 · inbound

Amplify Adjacent Token Differences: Enhancing Long Chain-of-Thought Reasoning with Shift-FFN cites this paper.

Amplify Adjacent Token Differences: Enhancing Long Chain-of-Thought Reasoning with Shift-FFN In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering

Reference 20

Resolution
unresolved
no resolver link, observed 2026-08-07T15:05:17.455869Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T15:05:17.455869Z digest=sha256:2a4698a9002df0b4a299878bfc5dbc7aacd46ec023f69d73993c66d3d842ded2

Observation 13348acd-44ee-4db0-94e9-24d1cfb78f51 · inbound

Improved Representation Steering for Language Models cites this paper.

Improved Representation Steering for Language Models In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering

Reference 26

Resolution
unresolved
no resolver link, observed 2026-08-07T13:51:30.523157Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T13:51:30.523157Z digest=sha256:2c023785faed108238dd81f201897d286a677579dd353f1117f696627ac39768

Observation 46401bc7-8027-46c6-92fc-cd407df171f5 · inbound

More Thinking, Less Seeing? Assessing Amplified Hallucination in Multimodal Reasoning Models cites this paper.

More Thinking, Less Seeing? Assessing Amplified Hallucination in Multimodal Reasoning Models In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering

Reference 17

Resolution
unresolved
no resolver link, observed 2026-08-07T14:51:32.648647Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T14:51:32.648647Z digest=sha256:736efa85bf49fc1b48783cc34ab62f87d769bb51f3348e4ba8f578724d80fafe

Observation 34ef731a-9211-40c9-bc3d-f65f1122aa5c · inbound

Mind the Quote: Enabling Quotation-Aware Dialogue in LLMs via Plug-and-Play Modules cites this paper.

Mind the Quote: Enabling Quotation-Aware Dialogue in LLMs via Plug-and-Play Modules In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering

Reference 10

Resolution
unresolved
no resolver link, observed 2026-08-07T12:35:30.348382Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T12:35:30.348382Z digest=sha256:d12c2ee42fbbb9b226fef972c41a28958f89ef7d0d19258f64cd846bb35a02b2

Observation fc7899e0-3550-4ab8-8833-1cc9e2d4d00b · inbound

Disentangled Safety Adapters Enable Efficient Guardrails and Flexible Inference-Time Alignment cites this paper.

Disentangled Safety Adapters Enable Efficient Guardrails and Flexible Inference-Time Alignment In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering

Reference 26

Resolution
verified exact
arxiv_id, observed 2026-05-19T11:53:03.556278Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-05-19T11:52:36.688263Z digest=sha256:e3aaf063773b8eb2c7a517f57e57ee210670cf54ca610c36d7a35d11125fe971

Observation 4a9a8fef-6870-4662-95a8-d5bcde2bd181 · inbound

Linear Representation Transferability Hypothesis: Leveraging Small Models to Steer Large Models cites this paper.

Linear Representation Transferability Hypothesis: Leveraging Small Models to Steer Large Models In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering

Reference 20

Resolution
unresolved
no resolver link, observed 2026-08-07T12:07:10.667466Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T12:07:10.667466Z digest=sha256:ca80695e9b2b0ea3c6aee9089fcbaea0007b4abeb6d1fe72f8236ba3ba21e2cf

Observation b6b49cb8-5d42-4e9f-acc5-1c7f8bbca5fc · inbound

Detoxification of Large Language Models through Output-layer Fusion with a Calibration Model cites this paper.

Detoxification of Large Language Models through Output-layer Fusion with a Calibration Model In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering

Reference 19

Resolution
unresolved
no resolver link, observed 2026-08-07T11:51:46.326752Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T11:51:46.326752Z digest=sha256:fc0411e9e4dc91990eb44597b95826273297d7992f8b0cd5c70cdde6509c4628

Observation c8c7bd07-5992-4538-bec5-e34a6126e830 · inbound

ConText: Driving In-context Learning for Text Removal and Segmentation cites this paper.

ConText: Driving In-context Learning for Text Removal and Segmentation In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering

Reference 36

Resolution
unresolved
no resolver link, observed 2026-08-07T11:01:09.872864Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T11:01:09.872864Z digest=sha256:f0b01ea1906cacabede7e4a02b6d3e7ee34575abe8e02b6d900a2c10863555aa

Observation f7ac5b78-383b-4761-9b8f-8c6144eb12a9 · inbound

Structured Pruning for Diverse Best-of-N Reasoning Optimization cites this paper.

Structured Pruning for Diverse Best-of-N Reasoning Optimization In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering

Reference 27

Resolution
unresolved
no resolver link, observed 2026-08-07T10:56:23.627880Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T10:56:23.627880Z digest=sha256:d711f7ff88f2dd8ed5535e27414b7b6644e0995377614f12782f7f8d356196b5

Observation 3a42dfd5-9585-43a1-9090-1856fb98ef65 · inbound

MemOS: A Memory OS for AI System cites this paper.

MemOS: A Memory OS for AI System In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering

Reference 36

Resolution
verified exact
arxiv_id, observed 2026-05-15T08:20:22.833049Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-05-15T08:20:22.658329Z digest=sha256:aba93149c655ea07e2d2eb95d4993cb3b98faf40fd5202e0e993929edc790b08

Observation 327146c7-48eb-4a8a-8264-e881845061bf · inbound

Improving Data and Parameter Efficiency of Neural Language Models Using Representation Analysis cites this paper.

Improving Data and Parameter Efficiency of Neural Language Models Using Representation Analysis In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering

Reference 136

Resolution
unresolved
no resolver link, observed 2026-08-06T17:03:45.327421Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T17:03:45.327421Z digest=sha256:ee4d20b92bb1b226b4807802f13dbbd8bc2bab91d340e991acd8daf4f2237548

Observation eca44023-bf62-424e-aa19-ddb49aec86b7 · inbound

DICE: Dynamic In-Context Example Selection in LLM Agents via Efficient Knowledge Transfer cites this paper.

DICE: Dynamic In-Context Example Selection in LLM Agents via Efficient Knowledge Transfer In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering

Reference 16

Resolution
unresolved
no resolver link, observed 2026-08-06T10:43:47.057229Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T10:43:47.057229Z digest=sha256:5c0e44b9f4032b86221be0f771daf262197c886901853131c1c32d8a2fe9538d

Observation ce154081-bdbc-45c6-8b3a-7996c2f6abac · inbound

Delta Activations: A Representation for Finetuned Large Language Models cites this paper.

Delta Activations: A Representation for Finetuned Large Language Models In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering

Reference 36

Resolution
unresolved
no resolver link, observed 2026-08-15T16:32:08.484913Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T16:32:08.484913Z digest=sha256:8af30acae5340055eb512bc80a65ef3c4e5db2d9e0bb97aef63657d9a31c2849

Observation 2337b863-f4c0-465d-94b7-14b5a3b857e8 · inbound

Steering Protein Language Models cites this paper.

Steering Protein Language Models In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering

Reference 19

Resolution
unresolved
no resolver link, observed 2026-08-06T21:10:12.041903Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T21:10:12.041903Z digest=sha256:2e4410f840ebff773fb2de963c9c3bd13bfcede6c223e1adf431802ff58b7340

Observation 40e699ce-3cc9-4428-8b40-8efbc7962d2e · inbound

HalluField: Detecting LLM Hallucinations via Field-Theoretic Modeling cites this paper.

HalluField: Detecting LLM Hallucinations via Field-Theoretic Modeling In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering

Reference 15

Resolution
unresolved
no resolver link, observed 2026-08-04T17:41:05.783412Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T17:41:05.783412Z digest=sha256:46db4907273c22037a8d5bd6fde4d46475d1ffd7b2b783fc0cf11d42e433d1ae

Observation 52ee78c3-2997-409b-9924-78f6d5982f6c · inbound

Train Once, Reuse Everywhere: Generalizable Implicit In-Context Learning by Routing Attention cites this paper.

Train Once, Reuse Everywhere: Generalizable Implicit In-Context Learning by Routing Attention In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering

Reference 2021

Resolution
unresolved
no resolver link, observed 2026-08-04T14:50:23.161687Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T14:50:23.161687Z digest=sha256:01afec652da72115da699ef6bc633274d0deda675a4e53dc6752286a5f11e55c

Observation 5fb89356-fb44-4344-87a7-242d05d1f85e · inbound

Localizing Task Recognition and Task Learning in In-Context Learning via Attention Head Analysis cites this paper.

Localizing Task Recognition and Task Learning in In-Context Learning via Attention Head Analysis In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering

Reference 23

Resolution
verified exact
arxiv_id, observed 2026-05-18T13:31:25.510244Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=arxiv_source observed=2026-05-18T13:26:59.080330Z digest=sha256:bd9634042c93ab15504f22418e6344b1ec124191a54b40efadccba43e7586337

Observation 539c78b4-de45-4f0d-8fe3-4bfce60e6c02 · inbound

Attention Misses Visual Risk: Risk-Adaptive Steering for Multimodal Safety Alignment cites this paper.

Attention Misses Visual Risk: Risk-Adaptive Steering for Multimodal Safety Alignment In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering

Reference 11

Resolution
unresolved
no resolver link, observed 2026-08-04T09:47:24.031032Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T09:47:24.031032Z digest=sha256:bd2e62dfba1645e9a307c4031e5d6c09b6f11d30c4b6ad2c1cadcb81392ed57e

Observation ce11184d-0dd8-4378-944d-a115cdbb2904 · inbound

The SuperActivator Mechanism: Transformers Concentrate Reliable Concept Signals in the Tail cites this paper.

The SuperActivator Mechanism: Transformers Concentrate Reliable Concept Signals in the Tail In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering

Reference 40

Resolution
unresolved
no resolver link, observed 2026-08-03T18:33:04.699292Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-03T18:33:04.699292Z digest=sha256:a8b4c942c0fc45cbf354d870487e6702db1e42eb093c83424a6b044c0a9dd2a5

Observation 6460bb0d-9fa6-48bf-b742-8b7056c618e6 · inbound

Dual Implications of Quark Mass Hierarchies to Flavor Structure cites this paper.

Dual Implications of Quark Mass Hierarchies to Flavor Structure In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering

Reference 19

Resolution
unresolved
no resolver link, observed 2026-07-13T13:46:54.451163Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-13T13:46:54.451163Z digest=sha256:fdf5f619c7439aa964b51add55950c4e5cf38f03bf82832f4d65ec8ff0761b4a

Observation defc13d3-1a0e-4e4e-806d-12132841e8b2 · inbound

Steerable but Not Decodable: Function Vectors Operate Beyond the Logit Lens cites this paper.

Steerable but Not Decodable: Function Vectors Operate Beyond the Logit Lens In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering

Reference 14

Resolution
verified exact
arxiv_id, observed 2026-05-13T21:03:20.265773Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-05-13T20:59:02.824707Z digest=sha256:c49ecec80bceeb02e3db795d67c6e894533a2dae9431d252623f094d7ecd1f36

Observation bdd0748e-49e0-45c9-8b73-1ab30ae45b5e · inbound

The Master Key Hypothesis: Unlocking Cross-Model Capability Transfer via Linear Subspace Alignment cites this paper.

The Master Key Hypothesis: Unlocking Cross-Model Capability Transfer via Linear Subspace Alignment In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering

Reference 41

Resolution
verified exact
arxiv_id, observed 2026-05-11T00:15:56.006285Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-05-10T18:36:44.401045Z digest=sha256:688920a382ab1a49ce3113bfe59d6ec3d63955dd2749a12278c9c9947c4d1284

Observation 0b68e652-64d0-4b27-baf8-f8e68998eb17 · inbound

Dictionary-Aligned Concept Control for Safeguarding Multimodal LLMs cites this paper.

Dictionary-Aligned Concept Control for Safeguarding Multimodal LLMs In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering

Reference 49

Resolution
verified exact
arxiv_id, observed 2026-05-11T05:35:57.471304Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-05-10T18:04:05.157103Z digest=sha256:8b2ae9621dc481c8d03221d1a816df1fe51b2c8cc00a008a8e1e7190f0748b5e

Observation 334865ff-b412-48c3-856c-941092cc637c · inbound

Exploring Language-Agnosticity in Function Vectors: A Case Study in Machine Translation cites this paper.

Exploring Language-Agnosticity in Function Vectors: A Case Study in Machine Translation In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering

Reference 24

Resolution
verified exact
arxiv_id, observed 2026-05-10T02:53:29.747800Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=arxiv_source observed=2026-05-10T02:49:55.908142Z digest=sha256:a6a64f45df4e65db0378620f958c1fdf3846f10626c73e4ab5cb196f41ef8413

Observation 81870eea-f9fb-44b0-a5c0-c6426976e57f · inbound

Prompt-Activation Duality: Improving Activation Steering via Attention-Level Interventions cites this paper.

Prompt-Activation Duality: Improving Activation Steering via Attention-Level Interventions In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering

Reference 11

Resolution
verified exact
arxiv_id, observed 2026-05-12T06:16:26.030861Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-05-12T04:27:15.490694Z digest=sha256:8db68058e803b8d0a8f4954310456b34eee555214e8404f68c7de6d325af2b9c

Observation 669109e9-ec9c-44db-81b3-840329cf9e75 · inbound

Prompt-Activation Duality: Improving Activation Steering via Attention-Level Interventions cites this paper.

Prompt-Activation Duality: Improving Activation Steering via Attention-Level Interventions In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering

Reference 11

Resolution
verified exact
arxiv_id, observed 2026-05-15T05:29:47.020172Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-05-15T05:27:59.011749Z digest=sha256:eb423a26158255a130a6cf8d0002c8133928c74bb1083a0d056e62921144b5c7

Observation 3af346b8-5948-4556-814e-d7408037faaf · inbound

Not All Tokens Matter Equally: Dynamic In-context Vector Distillation with Decisive-Token Supervision for Long-form Medical Report Generation cites this paper.

Not All Tokens Matter Equally: Dynamic In-context Vector Distillation with Decisive-Token Supervision for Long-form Medical Report Generation In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering

Reference 32

Resolution
verified exact
arxiv_id, observed 2026-06-29T18:43:50.990797Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-06-29T18:33:59.286276Z digest=sha256:6432af81b3de70f00eeffbf380700bfb5303968e8d5d6f60e0ace5c0355f21eb

Observation 96fae450-f46f-48e6-aa6a-a463c6257520 · inbound

LLM Self-Recognition: Steering and Retrieving Activation Signatures cites this paper.

LLM Self-Recognition: Steering and Retrieving Activation Signatures In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering

Reference 34

Resolution
verified exact
arxiv_id, observed 2026-06-28T01:41:29.213207Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=arxiv_source observed=2026-06-28T01:41:03.518190Z digest=sha256:4d927af8346b2a52726f187c6d384f7fe0043346e986d7150cd273cb6bc14a49

Observation 6749c684-80bb-4882-a0bf-98fbe9c87eaf · inbound

On The Effectiveness-Fluency Trade-Off In LLM Conditioning: A Systematic Study cites this paper.

On The Effectiveness-Fluency Trade-Off In LLM Conditioning: A Systematic Study In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering

Reference 26

Resolution
metadata mismatch
arxiv_id, observed 2026-07-03T11:18:03.197282Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=arxiv_source observed=2026-06-27T09:40:48.736006Z digest=sha256:6f8084e92e9ce6f64add48bb8dd29450d66691cb42c88af72441e0eb149d5651

Observation 24718092-8549-433d-824e-bf224489e6a6 · inbound

Prompt Compression via Activation Aggregation cites this paper.

Prompt Compression via Activation Aggregation In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering

Reference 19

Resolution
metadata mismatch
local_arxiv, observed 2026-07-10T08:06:57.842018Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=arxiv_source observed=2026-07-10T08:03:46.297577Z digest=sha256:d07f9961d66d6e52401cb7146b51176fb843d4d311ae6c8d232e4c492c2f6e56

Observation 49ac6977-4ad1-4e23-8520-9c4cb27db991 · inbound

Prompt Compression via Activation Aggregation cites this paper.

Prompt Compression via Activation Aggregation In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering

Reference 35

Resolution
verified exact
local_arxiv, observed 2026-07-10T08:06:57.492334Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=arxiv_source observed=2026-07-10T08:03:46.297577Z digest=sha256:def77e42ad5038a1525239be550bd2bd3bf4e3a63c078603be80ba133a734c63

Observation 940f1330-5b5b-425d-83c9-0135ab918dca · inbound

Probabilistic Concept-Aware Steering for Trustworthy LLM Inference cites this paper.

Probabilistic Concept-Aware Steering for Trustworthy LLM Inference In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering

Reference 30

Resolution
unresolved
no resolver link, observed 2026-08-02T13:56:43.816389Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T13:56:43.816389Z digest=sha256:c9524aee17b19522f353a44628e18be8a0db3d709ae1ef6644acfdea178bf1e7

Observation 29ef487a-54d6-4312-a7ab-910f7543db37 · inbound

Isotropy Cliffs: The Geometric Signature of Decision-Making in Large Language Models cites this paper.

Isotropy Cliffs: The Geometric Signature of Decision-Making in Large Language Models In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering

Reference 38

Resolution
unresolved
no resolver link, observed 2026-08-05T00:16:15.818556Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-05T00:16:15.818556Z digest=sha256:c45b2362eef42920b434f83e64baa8f83c5b35c1efd79c467d3e558b61539914

Observation 6a1adcf5-6235-4762-bb77-b65a4d00852a · inbound

When Is a Task Vector Enough? An Empirical Theory of Implicit Multimodal ICL cites this paper.

When Is a Task Vector Enough? An Empirical Theory of Implicit Multimodal ICL In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering

Reference 20

Resolution
unresolved
no resolver link, observed 2026-08-14T12:25:20.507829Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-14T12:25:20.507829Z digest=sha256:7dd0399b14cba03ff39ca8a7621c188d67bc19b7611e0e05914a59ffd4c7bc78