Paper Citation Record · LEDGER

Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safety

As of 13 August 2026, this Paper Citation Record lists 44 of 44 outbound references and 1 inbound Pith citation observation for arXiv:2506.05451.

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

pith.paper-citation-record.v1
2506.05451 v1

Coverage vector

measured 44 of 44 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T10:24:26.477946Z

measured 45 of 45 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-13T06:32:02.005865+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-03T05:45:42.313410Z

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

44 of 44 outbound references displayed

verified exact2
verified fuzzy10
unresolved29
parse uncertain0
malformed identifier0
metadata mismatch3

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation dbf922d8-bb63-4726-ace1-fb395551418c · outbound

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

Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safety Refusal in Language Models Is Mediated by a Single Direction

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T10:24:26.305781Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 062a7351-50e3-44b0-a0e1-ff7da1d591b2 · outbound

This paper cites Understanding Jailbreak Success: A Study of Latent Space Dynamics in Large Language Models.

Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safety Understanding Jailbreak Success: A Study of Latent Space Dynamics in Large Language Models

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T10:24:26.309978Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b58ac760-0795-4097-8005-5aaff2c6130e · outbound

This paper cites Discovering Latent Knowledge in Language Models Without Supervision.

Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safety Discovering Latent Knowledge in Language Models Without Supervision

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T10:24:26.314508Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a510d602-2812-4b6e-ad08-998edc02fac3 · outbound

This paper cites V ojtech Cahlik, Rodrigo Alves, and Pavel Kordik.

Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safety V ojtech Cahlik, Rodrigo Alves, and Pavel Kordik

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:24:27.266765Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation e97702f2-a65c-42fc-8bb2-dd2a8b388c03 · outbound

This paper cites Nitay Calderon and Roi Reichart.

Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safety Nitay Calderon and Roi Reichart

Reference 7

Resolution: verified exact; raw_fallback, observed 2026-08-07T10:24:27.077942Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation d8ea653f-a2ff-40a9-9f0f-2877412ba779 · outbound

This paper cites Improving Steering Vectors by Targeting Sparse Autoencoder Features.

Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safety Improving Steering Vectors by Targeting Sparse Autoencoder Features

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T10:24:26.327706Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c9e87b34-a8e6-4d4d-a985-b455905c92b1 · outbound

This paper cites Finetuning Language Models to Emit Linguistic Expressions of Uncertainty.

Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safety Finetuning Language Models to Emit Linguistic Expressions of Uncertainty

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T10:24:26.332694Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a08dd8f6-c46d-439f-8826-c1fd52b48c8c · outbound

This paper cites Faithful Reasoning Using Large Language Models.

Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safety Faithful Reasoning Using Large Language Models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T10:24:26.340928Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f977c197-fd2d-41d8-aa68-130cebbea1dc · outbound

This paper cites InThe Eleventh International Conference on Learning Rep- resentations.

Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safety InThe Eleventh International Conference on Learning Rep- resentations

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:24:27.244661Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 07d74fd0-9172-4674-a7fe-6404471bb4ba · outbound

This paper cites Discovering Variable Binding Circuitry with Desiderata.

Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safety Discovering Variable Binding Circuitry with Desiderata

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T10:24:26.349316Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c72c0a66-3748-4fb3-b5e9-3db3bf864d17 · outbound

This paper cites Studying Large Language Model Generalization with Influence Functions.

Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safety Studying Large Language Model Generalization with Influence Functions

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T10:24:26.357474Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2711a5e4-750b-4a0e-abe1-ae7a0bf9a485 · outbound

This paper cites InProceedings of the 37th Interna- tional Conference on Neural Information Processing Systems, NIPS ’23, Red Hook, NY , USA.

Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safety InProceedings of the 37th Interna- tional Conference on Neural Information Processing Systems, NIPS ’23, Red Hook, NY , USA

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:24:27.220441Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 55a3048b-7a0b-43f1-926f-4d7fd1a3dd6c · outbound

This paper cites Have Faith in Faithfulness: Going Beyond Circuit Overlap When Finding Model Mechanisms.

Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safety Have Faith in Faithfulness: Going Beyond Circuit Overlap When Finding Model Mechanisms

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T10:24:26.370726Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d010205d-0dd2-4b85-9ba4-9d27f86083e7 · outbound

This paper cites Zhengfu He, Xuyang Ge, Qiong Tang, Tianxiang Sun, Qinyuan Cheng, and Xipeng Qiu.

Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safety Zhengfu He, Xuyang Ge, Qiong Tang, Tianxiang Sun, Qinyuan Cheng, and Xipeng Qiu

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T10:24:26.375257Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3488b3e3-dca5-4d5e-8340-3e9f76278872 · outbound

This paper cites Alon Jacovi and Yoav Goldberg.

Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safety Alon Jacovi and Yoav Goldberg

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T10:24:26.380068Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d86483a8-da5a-482b-b580-4a6b03accbec · outbound

This paper cites How Large Language Models Encode Context Knowledge? A Layer-Wise Probing Study.

Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safety How Large Language Models Encode Context Knowledge? A Layer-Wise Probing Study

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T10:24:26.384700Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 271a24eb-f94f-46b3-b5ae-aaff77699d9a · outbound

This paper cites InProceedings of the 37th International Conference on Neural Information Processing Systems, NIPS ’23, Red Hook, NY , USA.

Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safety InProceedings of the 37th International Conference on Neural Information Processing Systems, NIPS ’23, Red Hook, NY , USA

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:24:27.209641Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 237d5644-9cb1-4701-bc63-1347536b7e4c · outbound

This paper cites InProceedings of the 61st Annual Meeting of the Association for Compu- tational Linguistics (Volume 3: System Demonstra- tions), pages 42–50, Toronto, Canada.

Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safety InProceedings of the 61st Annual Meeting of the Association for Compu- tational Linguistics (Volume 3: System Demonstra- tions), pages 42–50, Toronto, Canada

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:24:27.196551Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation d9c0bf9b-88c6-4aae-b144-8b6267082701 · outbound

This paper cites InThe Twelfth International Conference on Learning Repre- sentations.

Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safety InThe Twelfth International Conference on Learning Repre- sentations

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:24:27.184327Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 6532def3-7402-47d1-89d6-aeee8c336770 · outbound

This paper cites Rethinking Explainability as a Dialogue: A Practitioner's Perspective.

Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safety Rethinking Explainability as a Dialogue: A Practitioner's Perspective

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T10:24:26.403709Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f0a5476d-6ef2-4063-9cb9-57abc06527db · outbound

This paper cites HuDEx: Integrating Hallucination Detection and Explainability for Enhancing the Reliability of LLM responses.

Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safety HuDEx: Integrating Hallucination Detection and Explainability for Enhancing the Reliability of LLM responses

Reference 27

Resolution: metadata mismatch; local_arxiv, observed 2026-08-07T10:24:26.766381Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 9d704216-f085-43b4-ad3d-bf434267d1ac · outbound

This paper cites Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2.

Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safety Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T10:24:26.412268Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d9ef54eb-60ab-41e0-90dd-9dd62454179e · outbound

This paper cites Interpretable-by-Design Text Understanding with Iteratively Generated Concept Bottleneck.

Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safety Interpretable-by-Design Text Understanding with Iteratively Generated Concept Bottleneck

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T10:24:26.415954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b7f2c7cf-d0a3-41ba-bb9f-906cba85e495 · outbound

This paper cites Towards Principled Evaluations of Sparse Autoencoders for Interpretability and Control.

Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safety Towards Principled Evaluations of Sparse Autoencoders for Interpretability and Control

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-07T10:24:26.419920Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation de2e084d-6a75-4237-9fca-33dbbf571323 · outbound

This paper cites SaRO: Enhancing LLM Safety through Reasoning-based Alignment.

Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safety SaRO: Enhancing LLM Safety through Reasoning-based Alignment

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-07T10:24:26.427788Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 686d0779-98ad-4775-9f85-46cf60b7591e · outbound

This paper cites Gradient-Based Automated Iterative Recovery for Parameter-Efficient Tuning.

Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safety Gradient-Based Automated Iterative Recovery for Parameter-Efficient Tuning

Reference 33

Resolution: metadata mismatch; local_arxiv, observed 2026-08-07T10:24:26.697247Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation cbeb1e1e-31e7-498f-af5f-ca4aa00efc3b · outbound

This paper cites Steering Language Model Refusal with Sparse Autoencoders.

Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safety Steering Language Model Refusal with Sparse Autoencoders

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-07T10:24:26.435845Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 08cddfeb-c7d8-4643-b109-c0b071d77632 · outbound

This paper cites Refining Input Guardrails: Enhancing LLM-as-a-Judge Efficiency Through Chain-of-Thought Fine-Tuning and Alignment.

Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safety Refining Input Guardrails: Enhancing LLM-as-a-Judge Efficiency Through Chain-of-Thought Fine-Tuning and Alignment

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-07T10:24:26.440712Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d2f08816-1d81-41f5-87dd-077d24031298 · outbound

This paper cites RevPRAG: Revealing Poisoning Attacks in Retrieval-Augmented Generation through LLM Activation Analysis.

Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safety RevPRAG: Revealing Poisoning Attacks in Retrieval-Augmented Generation through LLM Activation Analysis

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-07T10:24:26.452708Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 25099a16-f626-442c-8027-75aa87f62c6f · outbound

This paper cites InICLR 2025 Workshop on Building Trust in Language Models and Applications.

Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safety InICLR 2025 Workshop on Building Trust in Language Models and Applications

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:24:27.160267Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 18f8d42c-9149-455b-a29f-653f71b8df80 · outbound

This paper cites Steering Language Models With Activation Engineering.

Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safety Steering Language Models With Activation Engineering

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-07T10:24:26.465201Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b7093f4e-d86c-4039-9e92-9ea347a812a3 · outbound

This paper cites an unresolved cited work.

Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safety Unresolved cited work

Reference 42

Resolution: unresolved; raw_fallback, observed 2026-08-07T10:24:27.148900Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 6077e1dc-c411-4eb3-8de1-7e23de6a6069 · outbound

This paper cites Using Mechanistic Interpretability to Craft Adversarial Attacks against Large Language Models.

Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safety Using Mechanistic Interpretability to Craft Adversarial Attacks against Large Language Models

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-07T10:24:26.474285Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d632adf3-891d-4c43-9da3-7e8ddee5ac65 · outbound

This paper cites Defensive Prompt Patch: A Robust and Interpretable Defense of LLMs against Jailbreak Attacks.

Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safety Defensive Prompt Patch: A Robust and Interpretable Defense of LLMs against Jailbreak Attacks

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-07T10:24:26.477946Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fb2c1e6d-62a1-48f1-99ca-61df1f20c819 · outbound

This paper cites why should i trust you?.

Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safety why should i trust you?

Reference 483

Resolution: verified exact; raw_fallback, observed 2026-08-07T10:24:26.660635Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 99d8ab01-3987-47fe-a284-cd5793d76918 · outbound

This paper cites Chain of Thought Still Thinks Fast: APriCoT Helps with Thinking Slow.

Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safety Chain of Thought Still Thinks Fast: APriCoT Helps with Thinking Slow

Reference 2013

Resolution: unresolved; no resolver link, observed 2026-08-07T10:24:26.423582Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 55ba416a-3575-4f8b-982a-9f11b3f56127 · outbound

This paper cites What do you learn from context? Probing for sentence structure in contextualized word representations.

Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safety What do you learn from context? Probing for sentence structure in contextualized word representations

Reference 2019

Resolution: unresolved; no resolver link, observed 2026-08-07T10:24:26.456815Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d9acd6c1-29b8-4742-8f4c-bda55b6e9ef2 · outbound

This paper cites In Proceedings of the 58th Annual Meeting of the Asso- ciation for Computational Linguistics, pages 5553– 5563, Online.

Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safety In Proceedings of the 58th Annual Meeting of the Asso- ciation for Computational Linguistics, pages 5553– 5563, Online

Reference 2020

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:24:27.232109Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 2848e556-47e8-4bc3-8182-b773c9fa1e82 · outbound

This paper cites Jacobian Sparse Autoencoders: Sparsify Computations, Not Just Activations.

Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safety Jacobian Sparse Autoencoders: Sparsify Computations, Not Just Activations

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-07T10:24:26.353163Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1215c80c-f397-4304-89cd-3a2e21d794a6 · outbound

This paper cites AtP*: An efficient and scalable method for localizing LLM behaviour to components.

Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safety AtP*: An efficient and scalable method for localizing LLM behaviour to components

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-07T10:24:26.388763Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2f1c746e-ede6-4330-bb77-3f4bf6832ede · outbound

This paper cites InAdvances in Neural Infor- mation Processing Systems, volume 36, pages 16318– 16352.

Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safety InAdvances in Neural Infor- mation Processing Systems, volume 36, pages 16318– 16352

Reference 2023

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:24:27.255379Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation ebd8f26f-5dc9-4d52-9ac6-bef8b3335c81 · outbound

This paper cites Get my drift? Catching LLM Task Drift with Activation Deltas.

Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safety Get my drift? Catching LLM Task Drift with Activation Deltas

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-07T10:24:26.300328Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 560521ff-a5b7-43da-a648-05155e0ef7b0 · outbound

This paper cites SAFE: A Sparse Autoencoder-Based Framework for Robust Query Enrichment and Hallucination Mitigation in LLMs.

Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safety SAFE: A Sparse Autoencoder-Based Framework for Robust Query Enrichment and Hallucination Mitigation in LLMs

Reference 2025

Resolution: metadata mismatch; local_arxiv, observed 2026-08-07T10:24:27.136657Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 9e69ad70-b6de-42ab-8d6e-6831fa30682f · outbound

This paper cites Aaquib Syed, Can Rager, and Arthur Conmy.

Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safety Aaquib Syed, Can Rager, and Arthur Conmy

Reference 3328

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:24:27.172301Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Pith citing papers

Observation c0ba13cc-7577-4cd3-9ca2-2dfa84908394 · inbound

Step-Wise Refusal Dynamics in Autoregressive and Diffusion Language Models cites this paper.

Step-Wise Refusal Dynamics in Autoregressive and Diffusion Language Models Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safety

Reference 2000

Resolution: unresolved; no resolver link, observed 2026-08-03T05:45:42.313410Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.