Paper Citation Record · LEDGER

Understanding (Un)Reliability of Steering Vectors in Language Models

As of 18 August 2026, this Paper Citation Record lists 37 of 37 outbound references and 11 inbound Pith citation observations for arXiv:2505.22637.

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

pith.paper-citation-record.v1
2505.22637 v1

Coverage vector

measured 37 of 37 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T13:10:08.895546Z

measured 48 of 48 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-18T06:34:40.430872+00:00

measured 11 of 11 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-15T15:00:38.060792Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-04T15:49:57.002506Z

Reference resolution

37 of 37 outbound references displayed

verified exact2
verified fuzzy6
unresolved28
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation bd450999-42e0-4f54-877d-862e670f8720 · outbound

This paper cites write newline.

Understanding (Un)Reliability of Steering Vectors in Language Models write newline

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T13:10:03.289827Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b12abee5-3591-465f-a777-29e583a26be2 · outbound

This paper cites Refusal in Language Models Is Mediated by a Single Direction.

Understanding (Un)Reliability of Steering Vectors in Language Models Refusal in Language Models Is Mediated by a Single Direction

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T13:10:03.419878Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4955598a-7f3d-400c-ae32-003701625648 · outbound

This paper cites Cats: Customizable abstractive topic-based summarization.

Understanding (Un)Reliability of Steering Vectors in Language Models Cats: Customizable abstractive topic-based summarization

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T13:10:03.548101Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6d857f70-6587-4148-a88f-847eab514349 · outbound

This paper cites NEWTS : A corpus for news topic-focused summarization.

Understanding (Un)Reliability of Steering Vectors in Language Models NEWTS : A corpus for news topic-focused summarization

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T13:10:03.715918Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8ae392d8-655e-4c49-a154-3e3524d501bf · outbound

This paper cites Controllable Topic-Focused Abstractive Summarization.

Understanding (Un)Reliability of Steering Vectors in Language Models Controllable Topic-Focused Abstractive Summarization

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T13:10:03.927972Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7062c719-3fd9-49f0-ac2d-cf6212c10207 · outbound

This paper cites Text simplification via adaptive teaching.

Understanding (Un)Reliability of Steering Vectors in Language Models Text simplification via adaptive teaching

Reference 6

Resolution: verified exact; doi, observed 2026-08-07T13:10:09.638480Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation e5da340c-198b-477c-b853-a1b095413748 · outbound

This paper cites SIMSUM : Document-level text simplification via simultaneous summarization.

Understanding (Un)Reliability of Steering Vectors in Language Models SIMSUM : Document-level text simplification via simultaneous summarization

Reference 7

Resolution: verified exact; doi, observed 2026-08-07T13:10:09.260944Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 2a3eaa2a-7361-4b48-a088-8e8edad3ab5a · outbound

This paper cites A sober look at steering vectors for llms.

Understanding (Un)Reliability of Steering Vectors in Language Models A sober look at steering vectors for llms

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:10:12.329122Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 7110b613-adc6-48fa-a5cd-ec86b0bfb4b0 · outbound

This paper cites Comparing Bottom-Up and Top-Down Steering Approaches on In-Context Learning Tasks.

Understanding (Un)Reliability of Steering Vectors in Language Models Comparing Bottom-Up and Top-Down Steering Approaches on In-Context Learning Tasks

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T13:10:04.575056Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 30fa9f24-32c4-46c4-b4aa-88e21828886b · outbound

This paper cites Personalized Steering of Large Language Models: Versatile Steering Vectors Through Bi-directional Preference Optimization.

Understanding (Un)Reliability of Steering Vectors in Language Models Personalized Steering of Large Language Models: Versatile Steering Vectors Through Bi-directional Preference Optimization

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T13:10:04.717862Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3701d840-1f93-448f-a62d-ef5ace6f7da4 · outbound

This paper cites In-context learning creates task vectors.

Understanding (Un)Reliability of Steering Vectors in Language Models In-context learning creates task vectors

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T13:10:04.898405Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 11affa31-d0f5-42b0-847d-02f596676574 · outbound

This paper cites Measuring massive multitask language understanding.

Understanding (Un)Reliability of Steering Vectors in Language Models Measuring massive multitask language understanding

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T13:10:04.974038Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 87fc6599-bc67-431b-ba03-3660781afacb · outbound

This paper cites Style Vectors for Steering Generative Large Language Models.

Understanding (Un)Reliability of Steering Vectors in Language Models Style Vectors for Steering Generative Large Language Models

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:10:11.949019Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 514b7c2d-d754-4bc9-8e5e-7bd005f009f9 · outbound

This paper cites Steering clear: A systematic study of activation steering in a toy setup.

Understanding (Un)Reliability of Steering Vectors in Language Models Steering clear: A systematic study of activation steering in a toy setup

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:10:11.664519Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 7da431f6-36ab-49cf-a44e-f9ce9e74cf2a · outbound

This paper cites Inference-time intervention: Eliciting truthful answers from a language model.

Understanding (Un)Reliability of Steering Vectors in Language Models Inference-time intervention: Eliciting truthful answers from a language model

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T13:10:05.387255Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 49a3bbf8-7c4b-4cd6-bbe5-b215a7fb408f · outbound

This paper cites The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets.

Understanding (Un)Reliability of Steering Vectors in Language Models The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T13:10:05.520729Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 58eb0b15-9f5f-4252-a074-fa17f2772e13 · outbound

This paper cites The geometry of truth: Emergent linear structure in large language model representations of true/false datasets.

Understanding (Un)Reliability of Steering Vectors in Language Models The geometry of truth: Emergent linear structure in large language model representations of true/false datasets

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:10:11.347820Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 0bc45b64-edcd-4965-a435-cc549a2067eb · outbound

This paper cites Refusal in LLMs is an Affine Function.

Understanding (Un)Reliability of Steering Vectors in Language Models Refusal in LLMs is an Affine Function

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T13:10:05.846705Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 89d8d63f-d64f-4a5e-93a8-1b2ced9f909a · outbound

This paper cites Towards Reliable Evaluation of Behavior Steering Interventions in LLMs.

Understanding (Un)Reliability of Steering Vectors in Language Models Towards Reliable Evaluation of Behavior Steering Interventions in LLMs

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T13:10:06.057729Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 116acc5e-5900-466e-bca0-86616e6a68de · outbound

This paper cites Steering llama 2 via contrastive activation addition.

Understanding (Un)Reliability of Steering Vectors in Language Models Steering llama 2 via contrastive activation addition

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T13:10:06.173597Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dad2db02-e247-492c-b995-e6a20608a38d · outbound

This paper cites Discovering Language Model Behaviors with Model-Written Evaluations, Toronto, Canada, July 2023.

Understanding (Un)Reliability of Steering Vectors in Language Models Discovering Language Model Behaviors with Model-Written Evaluations, Toronto, Canada, July 2023

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T13:10:06.293291Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 83e09f5f-6664-46c3-bb9c-07f5ade319fd · outbound

This paper cites Representation surgery: Theory and practice of affine steering.

Understanding (Un)Reliability of Steering Vectors in Language Models Representation surgery: Theory and practice of affine steering

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:10:10.985849Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation e234c100-7387-4af3-943b-c7b0bbf7c2df · outbound

This paper cites an unresolved cited work.

Understanding (Un)Reliability of Steering Vectors in Language Models Unresolved cited work

Reference 23

Resolution: unresolved; raw_fallback, observed 2026-08-07T13:10:10.614343Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation df5ab5eb-3fdb-4ef0-95a3-796919775ffb · outbound

This paper cites Extracting Latent Steering Vectors from Pretrained Language Models.

Understanding (Un)Reliability of Steering Vectors in Language Models Extracting Latent Steering Vectors from Pretrained Language Models

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T13:10:06.744243Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e27cad75-e919-4e0a-968b-829da0f359a5 · outbound

This paper cites Analysing the generalisation and reliability of steering vectors.

Understanding (Un)Reliability of Steering Vectors in Language Models Analysing the generalisation and reliability of steering vectors

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T13:10:06.928187Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 012e9b4e-7a8b-4feb-b47d-7865abd582f6 · outbound

This paper cites Linear Representations of Sentiment in Large Language Models.

Understanding (Un)Reliability of Steering Vectors in Language Models Linear Representations of Sentiment in Large Language Models

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T13:10:07.072130Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0b1763f6-acb5-41dc-871c-d36007e80b69 · outbound

This paper cites Hollinsworth, Atticus Geiger, and Neel Nanda.

Understanding (Un)Reliability of Steering Vectors in Language Models Hollinsworth, Atticus Geiger, and Neel Nanda

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T13:10:07.202080Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 96dbf721-bcbc-4538-8d96-a39327a76187 · outbound

This paper cites Function Vectors in Large Language Models.

Understanding (Un)Reliability of Steering Vectors in Language Models Function Vectors in Large Language Models

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T13:10:07.335261Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1608ff49-3205-4878-9d8d-633a7ba8e9d4 · outbound

This paper cites Function vectors in large language models.

Understanding (Un)Reliability of Steering Vectors in Language Models Function vectors in large language models

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T13:10:07.486495Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 71d1e75e-8ae7-4697-9eaf-bf08c20d67c3 · outbound

This paper cites Llama 2: Open Foundation and Fine-Tuned Chat Models.

Understanding (Un)Reliability of Steering Vectors in Language Models Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-07T13:10:07.663220Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f0ddce0c-bb20-4bec-a1c4-608a2c6799e3 · outbound

This paper cites Activation addition: Steering language models without optimization.

Understanding (Un)Reliability of Steering Vectors in Language Models Activation addition: Steering language models without optimization

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:10:10.366568Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation b11d6994-d56f-4cb9-ba92-94582b225ee5 · outbound

This paper cites Controllable text summarization: Unraveling challenges, approaches, and prospects - a survey.

Understanding (Un)Reliability of Steering Vectors in Language Models Controllable text summarization: Unraveling challenges, approaches, and prospects - a survey

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-07T13:10:07.935345Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e52a79ce-8217-4802-8fe8-e87911df09bb · outbound

This paper cites A comprehensive survey on process-oriented automatic text summarization with exploration of llm-based methods, 2025.

Understanding (Un)Reliability of Steering Vectors in Language Models A comprehensive survey on process-oriented automatic text summarization with exploration of llm-based methods, 2025

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-07T13:10:08.060573Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 30e6f97d-3aac-4854-8e10-5df3e4d72504 · outbound

This paper cites Representation Engineering: A Top-Down Approach to AI Transparency.

Understanding (Un)Reliability of Steering Vectors in Language Models Representation Engineering: A Top-Down Approach to AI Transparency

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-07T13:10:08.399853Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8b8eca33-f2ad-4632-8d6c-55f6e08636e5 · outbound

This paper cites @esa (Ref.

Understanding (Un)Reliability of Steering Vectors in Language Models @esa (Ref

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-07T13:10:08.563640Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 400ebaa9-c888-45ae-ae67-5b09f2f630c2 · outbound

This paper cites an unresolved cited work.

Understanding (Un)Reliability of Steering Vectors in Language Models Unresolved cited work

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-07T13:10:08.737088Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d56fbc92-ed8d-4e88-b60b-b678e757acee · outbound

This paper cites 3!( 4˜ "3!( 4˒.

Understanding (Un)Reliability of Steering Vectors in Language Models 3!( 4˜ "3!( 4˒

Reference 38

Resolution: malformed identifier; no resolver link, observed 2026-08-07T13:10:08.895546Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 70274d98-43c8-4562-bdd8-b51bc6ccbdfe · inbound

RouteHijack: Routing-Aware Attack on Mixture-of-Experts LLMs cites this paper.

RouteHijack: Routing-Aware Attack on Mixture-of-Experts LLMs Understanding (Un)Reliability of Steering Vectors in Language Models

Reference 5

Resolution: verified exact; arxiv_id, observed 2026-05-11T15:46:13.825157Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 69162c32-1c61-409f-b86e-267231d7d9cd · inbound

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

Prompt-Activation Duality: Improving Activation Steering via Attention-Level Interventions Understanding (Un)Reliability of Steering Vectors in Language Models

Reference 3

Resolution: verified exact; arxiv_id, observed 2026-05-12T06:16:25.939080Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 71c24dca-f1f9-44a7-b847-9c1a5afd1c8e · inbound

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

Prompt-Activation Duality: Improving Activation Steering via Attention-Level Interventions Understanding (Un)Reliability of Steering Vectors in Language Models

Reference 3

Resolution: verified exact; arxiv_id, observed 2026-05-15T05:29:47.076007Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 1e77b7e1-96eb-4d6f-92e0-237f38dca4b5 · inbound

When Is Rank-1 Steering Cheap? Geometry, Granularity, and Budgeted Search cites this paper.

When Is Rank-1 Steering Cheap? Geometry, Granularity, and Budgeted Search Understanding (Un)Reliability of Steering Vectors in Language Models

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-05-20T22:39:10.703623Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation b48fd55b-ee3c-4512-a253-0d40a3b82cbb · inbound

When Is Rank-1 Steering Cheap? Geometry, Granularity, and Budgeted Search cites this paper.

When Is Rank-1 Steering Cheap? Geometry, Granularity, and Budgeted Search Understanding (Un)Reliability of Steering Vectors in Language Models

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-05-22T10:01:23.525559Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 3f421cf8-48ca-41b2-a447-55420c0c24c7 · inbound

Temporal Preference Concepts and their Functions in a Large Language Model cites this paper.

Temporal Preference Concepts and their Functions in a Large Language Model Understanding (Un)Reliability of Steering Vectors in Language Models

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-07-01T14:05:47.215257Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 19796388-a601-4242-a1c8-02fb3a196a44 · inbound

Temporal Preference Concepts and their Functions in a Large Language Model cites this paper.

Temporal Preference Concepts and their Functions in a Large Language Model Understanding (Un)Reliability of Steering Vectors in Language Models

Reference 10

Resolution: unresolved; no resolver link, observed 2026-07-12T17:03:44.315006Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d460774b-6a78-4912-8e56-f903b96b75df · inbound

Adversarial Robustness of Activation Steering in Large Language Models cites this paper.

Adversarial Robustness of Activation Steering in Large Language Models Understanding (Un)Reliability of Steering Vectors in Language Models

Reference 29

Resolution: metadata mismatch; arxiv_id, observed 2026-07-02T16:37:09.432517Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 4d6c0238-a48e-4825-ae00-cabcc32cf3ed · inbound

Detecting and Controlling Sycophancy with Cascading Linear Features cites this paper.

Detecting and Controlling Sycophancy with Cascading Linear Features Understanding (Un)Reliability of Steering Vectors in Language Models

Reference 2

Resolution: verified exact; arxiv_id, observed 2026-07-04T15:49:57.005467Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation ab15ab25-369b-452d-91c7-3fb5f45bc50c · inbound

Conditional Optimal Bridge for Riemannian Activation Steering cites this paper.

Conditional Optimal Bridge for Riemannian Activation Steering Understanding (Un)Reliability of Steering Vectors in Language Models

Reference 3

Resolution: unresolved; no resolver link, observed 2026-07-14T11:08:17.571722Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b94d2b41-60e5-42a2-a7e1-dbca2818c079 · inbound

Inverted Detection and Control in Steering Vectors cites this paper.

Inverted Detection and Control in Steering Vectors Understanding (Un)Reliability of Steering Vectors in Language Models

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-15T15:00:38.060792Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.