Safety Cost of Steering Vectors Is Separable and Reducible | Paper Citation Record

Observation 6b0a3595-25cf-4b96-8bae-d1df1fbf1a37 · outbound

This paper cites Attention is All you Need , url =.

Safety Cost of Steering Vectors Is Separable and Reducible Attention is All you Need , url =

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-14T04:44:58.069672Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5ee90979-e265-4896-8e1c-a90793e526ea · outbound

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

Safety Cost of Steering Vectors Is Separable and Reducible Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-14T04:44:58.075662Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9e54f4f1-56d5-415f-98d1-16bae24abb78 · outbound

This paper cites Gemma: Open Models Based on Gemini Research and Technology.

Safety Cost of Steering Vectors Is Separable and Reducible Gemma: Open Models Based on Gemini Research and Technology

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-14T04:44:58.080013Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 15adaf5f-5ffa-4866-a24d-5954e67e3a65 · outbound

This paper cites 2025 , eprint=.

Safety Cost of Steering Vectors Is Separable and Reducible 2025 , eprint=

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-14T04:44:58.084350Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cb77b161-9b90-4527-a430-9dbba25141b1 · outbound

This paper cites Advances in Neural Information Processing Systems , volume=.

Safety Cost of Steering Vectors Is Separable and Reducible Advances in Neural Information Processing Systems , volume=

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-14T04:44:58.088154Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9e4b130f-620f-4bf5-8136-6b48d527abc0 · outbound

This paper cites Advances in Neural Information Processing Systems , volume=.

Safety Cost of Steering Vectors Is Separable and Reducible Advances in Neural Information Processing Systems , volume=

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-14T04:44:58.091879Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 25d2128f-3e05-4270-af88-9c949ab2d97e · outbound

This paper cites Advances in Neural Information Processing Systems , volume=.

Safety Cost of Steering Vectors Is Separable and Reducible Advances in Neural Information Processing Systems , volume=

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-14T04:44:58.095867Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 18057188-a2c7-490e-bff5-632c5c2abbd4 · outbound

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

Safety Cost of Steering Vectors Is Separable and Reducible Extracting Latent Steering Vectors from Pretrained Language Models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-14T04:44:58.100168Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eb946e4f-e0e3-4480-80b8-0743a37fbdad · outbound

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

Safety Cost of Steering Vectors Is Separable and Reducible Representation Engineering: A Top-Down Approach to AI Transparency

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-14T04:44:58.104113Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cae11233-2f2a-4776-9727-3fabb1aa37cf · outbound

This paper cites Steering Language Models With Activation Engineering.

Safety Cost of Steering Vectors Is Separable and Reducible Steering Language Models With Activation Engineering

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-14T04:44:58.108286Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 01d482e5-3fb7-4a60-b13a-2c00c517529f · outbound

This paper cites Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , pages=.

Safety Cost of Steering Vectors Is Separable and Reducible Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , pages=

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-14T04:44:58.112470Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 89d40b0a-aac5-4717-bc22-07248c76fd78 · outbound

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

Safety Cost of Steering Vectors Is Separable and Reducible Improving Steering Vectors by Targeting Sparse Autoencoder Features

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-14T04:44:58.116351Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 73648d17-d5b9-4a10-b0bf-ce529f8796c1 · outbound

This paper cites Persona Vectors: Monitoring and Controlling Character Traits in Language Models.

Safety Cost of Steering Vectors Is Separable and Reducible Persona Vectors: Monitoring and Controlling Character Traits in Language Models

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-14T04:44:58.120327Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c008a0e7-ba5d-4043-b214-8b72b21c2345 · outbound

This paper cites Advances in Neural Information Processing Systems , volume=.

Safety Cost of Steering Vectors Is Separable and Reducible Advances in Neural Information Processing Systems , volume=

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-14T04:44:58.124548Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9afda2f6-2014-4456-9ff3-22abd9228a9c · outbound

This paper cites The Thirteenth International Conference on Learning Representations , year=.

Safety Cost of Steering Vectors Is Separable and Reducible The Thirteenth International Conference on Learning Representations , year=

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-14T04:44:58.128132Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8fa836d6-bbb3-4caa-b8dd-07dc6aa0bc89 · outbound

This paper cites Enhancing Instruction Following of.

Safety Cost of Steering Vectors Is Separable and Reducible Enhancing Instruction Following of

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:44:59.125238Z

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 8ecf02e8-fa6d-4d9b-8d06-f9604c150b1f · outbound

This paper cites 2023 , journal=.

Safety Cost of Steering Vectors Is Separable and Reducible 2023 , journal=

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-14T04:44:58.135521Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7ae156ad-4870-4a2d-ac7d-22bc5d1d371d · outbound

This paper cites 2022 , eprint=.

Safety Cost of Steering Vectors Is Separable and Reducible 2022 , eprint=

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-14T04:44:58.139616Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 075c4eae-4428-4dc7-baa5-bee3b7a51309 · outbound

This paper cites Shaping the Safety Boundaries: Understanding and Defending Against Jailbreaks in Large Language Models.

Safety Cost of Steering Vectors Is Separable and Reducible Shaping the Safety Boundaries: Understanding and Defending Against Jailbreaks in Large Language Models

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-14T04:44:58.143936Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b663ca64-d205-4d82-9415-694fccab0b4a · outbound

This paper cites T oxic C hat: Unveiling Hidden Challenges of Toxicity Detection in Real-World User- AI Conversation.

Safety Cost of Steering Vectors Is Separable and Reducible T oxic C hat: Unveiling Hidden Challenges of Toxicity Detection in Real-World User- AI Conversation

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-14T04:44:58.148478Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7eea9258-01ec-481e-852d-dbba514e5f92 · outbound

This paper cites All Languages Matter: On the Multilingual Safety of Large Language Models.

Safety Cost of Steering Vectors Is Separable and Reducible All Languages Matter: On the Multilingual Safety of Large Language Models

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-14T04:44:58.152421Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f7119d2e-4851-4722-ab45-661270b2ff87 · outbound

This paper cites Navigating the O ver K ill in Large Language Models.

Safety Cost of Steering Vectors Is Separable and Reducible Navigating the O ver K ill in Large Language Models

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-14T04:44:58.156366Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 32754f19-0d2b-4789-a3b2-ae984f93a79f · outbound

This paper cites Hashimoto , title =.

Safety Cost of Steering Vectors Is Separable and Reducible Hashimoto , title =

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-14T04:44:58.160248Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 94241870-a6df-41da-bfeb-8d4c5a4201f0 · outbound

This paper cites Forty-first International Conference on Machine Learning , year=.

Safety Cost of Steering Vectors Is Separable and Reducible Forty-first International Conference on Machine Learning , year=

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:44:59.079402Z

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 d7a3e25d-aa33-485e-8c42-459a7f8535bc · outbound

This paper cites The Thirty-eighth Annual Conference on Neural Information Processing Systems , year=.

Safety Cost of Steering Vectors Is Separable and Reducible The Thirty-eighth Annual Conference on Neural Information Processing Systems , year=

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:44:59.053517Z

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 ed243415-bec3-4744-82ab-1d7ecbbf84b1 · outbound

This paper cites The Thirty-eighth Annual Conference on Neural Information Processing Systems , year=.

Safety Cost of Steering Vectors Is Separable and Reducible The Thirty-eighth Annual Conference on Neural Information Processing Systems , year=

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:44:59.002337Z

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 255b0705-5024-4ee7-931b-aa2d8c8d0819 · outbound

This paper cites 2026 , eprint=.

Safety Cost of Steering Vectors Is Separable and Reducible 2026 , eprint=

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:44:58.988260Z

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 2fd4ba01-8790-4f53-b36c-501e6b556519 · outbound

This paper cites Galichin and Alexey Dontsov and Oleg Rogov and Ivan Oseledets and Elena Tutubalina , year=.

Safety Cost of Steering Vectors Is Separable and Reducible Galichin and Alexey Dontsov and Oleg Rogov and Ivan Oseledets and Elena Tutubalina , year=

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:44:58.974751Z

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 2de56627-8e64-4b91-9058-be7a59c9429b · outbound

This paper cites Steering Safely or Off a Cliff? Rethinking Specificity and Robustness in Inference-Time Interventions.

Safety Cost of Steering Vectors Is Separable and Reducible Steering Safely or Off a Cliff? Rethinking Specificity and Robustness in Inference-Time Interventions

Reference 29

Resolution: verified exact; doi, observed 2026-08-14T04:44:58.390938Z

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 80cc9287-06f3-4ef2-b8ef-86a26d9c8f84 · outbound

This paper cites arXiv preprint arXiv:2602.04896 , year=.

Safety Cost of Steering Vectors Is Separable and Reducible arXiv preprint arXiv:2602.04896 , year=

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-14T04:44:58.184795Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 45784172-7bc8-4256-b7d9-2c6a48157d54 · outbound

This paper cites One-shot Optimized Steering Vectors Mediate Safety-relevant Behaviors in.

Safety Cost of Steering Vectors Is Separable and Reducible One-shot Optimized Steering Vectors Mediate Safety-relevant Behaviors in

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-14T04:44:58.188221Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 706b1195-287e-44f6-b530-e58817c21317 · outbound

This paper cites and Askell, Amanda and Grosse, Roger and Hernandez, Danny and Ganguli, Deep and Hubinger, Evan and Schiefer, Nicholas and Kaplan, Jared.

Safety Cost of Steering Vectors Is Separable and Reducible and Askell, Amanda and Grosse, Roger and Hernandez, Danny and Ganguli, Deep and Hubinger, Evan and Schiefer, Nicholas and Kaplan, Jared

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-14T04:44:58.191948Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e0e3fb9-6610-48ce-b8ad-b5a591bf6c49 · outbound

This paper cites Jailbroken: How Does.

Safety Cost of Steering Vectors Is Separable and Reducible Jailbroken: How Does

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-14T04:44:58.195703Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f87de4cf-3913-4d79-9c77-b66efd4cd784 · outbound

This paper cites A Language Model.

Safety Cost of Steering Vectors Is Separable and Reducible A Language Model

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:44:58.909472Z

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 3d58c979-074f-428b-999e-5ad2cba1edda · outbound

This paper cites 2024 , eprint=.

Safety Cost of Steering Vectors Is Separable and Reducible 2024 , eprint=

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:44:58.896665Z

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 e49f08d1-4a84-41f1-bc76-cd76dca32f18 · outbound

This paper cites Extending Activation Steering to Broad Skills and Multiple Behaviours.

Safety Cost of Steering Vectors Is Separable and Reducible Extending Activation Steering to Broad Skills and Multiple Behaviours

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-14T04:44:58.207444Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4fefd14e-4867-48e0-ad2b-b93ac1bb2d69 · outbound

This paper cites International Conference on Learning Representations , year=.

Safety Cost of Steering Vectors Is Separable and Reducible International Conference on Learning Representations , year=

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-14T04:44:58.211314Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 73674e86-9b48-4d89-97e7-dc55c7cc6fb0 · outbound

This paper cites Shifting Perspectives: Steering Vectors for Robust Bias Mitigation in LLM s.

Safety Cost of Steering Vectors Is Separable and Reducible Shifting Perspectives: Steering Vectors for Robust Bias Mitigation in LLM s

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-14T04:44:58.214871Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1d9b0d78-124b-4829-a296-66abcdcc0bfe · outbound

This paper cites Causal Representation Learning Workshop at NeurIPS 2023 , year=.

Safety Cost of Steering Vectors Is Separable and Reducible Causal Representation Learning Workshop at NeurIPS 2023 , year=

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-14T04:44:58.218421Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c5e796dc-dd05-4a32-8ef3-30c9704bdbfb · outbound

This paper cites Advances in Neural Information Processing Systems , volume=.

Safety Cost of Steering Vectors Is Separable and Reducible Advances in Neural Information Processing Systems , volume=

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-14T04:44:58.222241Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b7772b23-76ed-4970-9ef6-41dfb15d236d · outbound

This paper cites Forty-second International Conference on Machine Learning , year=.

Safety Cost of Steering Vectors Is Separable and Reducible Forty-second International Conference on Machine Learning , year=

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-14T04:44:58.226158Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f663d19b-f7ac-4241-ac4f-7a9f0e9c67b2 · outbound

This paper cites The Llama 3 Herd of Models.

Safety Cost of Steering Vectors Is Separable and Reducible The Llama 3 Herd of Models

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-14T04:44:58.230199Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e11ce6e4-d896-4a6c-960a-ef2c6f45f358 · outbound

This paper cites T rivia QA : A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension.

Safety Cost of Steering Vectors Is Separable and Reducible T rivia QA : A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-14T04:44:58.234291Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f1f24fc2-ed3b-40c3-84be-e40883611be9 · outbound

This paper cites 2023 , eprint=.

Safety Cost of Steering Vectors Is Separable and Reducible 2023 , eprint=

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-14T04:44:58.238285Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 62cf5ce7-9b4b-46a6-87f3-0d11307c5d8f · outbound

This paper cites 2021 , eprint=.

Safety Cost of Steering Vectors Is Separable and Reducible 2021 , eprint=

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-14T04:44:58.242046Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4f8d5cda-479c-4719-801d-aeb6f4f4daa4 · outbound

This paper cites XST est: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models.

Safety Cost of Steering Vectors Is Separable and Reducible XST est: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-14T04:44:58.245706Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d456ec2a-e16d-481a-9cc4-379a8c0f5c3a · outbound

This paper cites Universal and Transferable Adversarial Attacks on Aligned Language Models.

Safety Cost of Steering Vectors Is Separable and Reducible Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-14T04:44:58.250498Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0abed703-b32b-499e-9348-b5d806c78691 · outbound

This paper cites an unresolved cited work.

Safety Cost of Steering Vectors Is Separable and Reducible Unresolved cited work

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-14T04:44:58.254479Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 269d91e3-3736-49d3-81fc-f2a130df5a3a · outbound

This paper cites R0-FoMo:Robustness of Few-shot and Zero-shot Learning in Large Foundation Models , year=.

Safety Cost of Steering Vectors Is Separable and Reducible R0-FoMo:Robustness of Few-shot and Zero-shot Learning in Large Foundation Models , year=

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:44:58.814378Z

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 96679bdd-f053-418f-b118-446489a642e9 · outbound

This paper cites 2025 , url=.

Safety Cost of Steering Vectors Is Separable and Reducible 2025 , url=

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:44:58.801086Z

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 8bd88d72-2a38-44cc-91aa-ccb74a53b6cc · outbound

This paper cites Forty-first International Conference on Machine Learning , year=.

Safety Cost of Steering Vectors Is Separable and Reducible Forty-first International Conference on Machine Learning , year=

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:44:58.788679Z

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 fb174bc8-eaf8-4903-bf23-f025f5f71ac5 · outbound

This paper cites Catastrophic Jailbreak of Open-source.

Safety Cost of Steering Vectors Is Separable and Reducible Catastrophic Jailbreak of Open-source

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:44:58.776169Z

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 af89223c-df78-44a4-9f54-abb727afb183 · outbound

This paper cites SALAD -Bench: A Hierarchical and Comprehensive Safety Benchmark for Large Language Models.

Safety Cost of Steering Vectors Is Separable and Reducible SALAD -Bench: A Hierarchical and Comprehensive Safety Benchmark for Large Language Models

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-14T04:44:58.272406Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8cf8463b-2968-43d0-a2be-cd5e16be909c · outbound

This paper cites HuggingFace's Transformers: State-of-the-art Natural Language Processing.

Safety Cost of Steering Vectors Is Separable and Reducible HuggingFace's Transformers: State-of-the-art Natural Language Processing

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-14T04:44:58.275803Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 32aaf8e1-d15f-4f0a-82d0-dc4eb0904cca · outbound

This paper cites Advances in neural information processing systems , volume=.

Safety Cost of Steering Vectors Is Separable and Reducible Advances in neural information processing systems , volume=

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-14T04:44:58.279360Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e71cd014-de19-40be-8ccf-21ec28919d2a · outbound

This paper cites an unresolved cited work.

Safety Cost of Steering Vectors Is Separable and Reducible Unresolved cited work

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-14T04:44:58.282942Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bd8f34f2-074b-49e3-8515-c3bb652e6d5b · outbound

This paper cites The Hidden Dimensions of.

Safety Cost of Steering Vectors Is Separable and Reducible The Hidden Dimensions of

Reference 57

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:44:58.746252Z

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 6c670f14-e33a-44c4-9ee0-d4a8055c3505 · outbound

This paper cites Forty-first International Conference on Machine Learning , year=.

Safety Cost of Steering Vectors Is Separable and Reducible Forty-first International Conference on Machine Learning , year=

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:44:58.733261Z

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 01a74307-033e-4f71-a157-226eae9657e6 · outbound

This paper cites Analysing the Safety Pitfalls of Steering Vectors.

Safety Cost of Steering Vectors Is Separable and Reducible Analysing the Safety Pitfalls of Steering Vectors

Reference 59

Resolution: verified exact; doi, observed 2026-08-14T04:44:58.343097Z

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 d24437ab-673e-4137-b2bb-f2b12bf65c62 · outbound

This paper cites Thirty-seventh Conference on Neural Information Processing Systems , year=.

Safety Cost of Steering Vectors Is Separable and Reducible Thirty-seventh Conference on Neural Information Processing Systems , year=

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-14T04:44:58.296986Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 64ae7538-fd39-4197-a598-a2ea13ffa405 · outbound

This paper cites Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned.

Safety Cost of Steering Vectors Is Separable and Reducible Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-14T04:44:58.300537Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3d603197-bf70-40cd-8097-d0ee10d7e7f2 · outbound

This paper cites Finetuned Language Models Are Zero-Shot Learners.

Safety Cost of Steering Vectors Is Separable and Reducible Finetuned Language Models Are Zero-Shot Learners

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-14T04:44:58.304233Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 812a3ec6-0090-474a-b052-481730b4e42b · outbound

This paper cites BeaverTails: Towards Improved Safety Alignment of LLM via a Human-Preference Dataset , url =.

Safety Cost of Steering Vectors Is Separable and Reducible BeaverTails: Towards Improved Safety Alignment of LLM via a Human-Preference Dataset , url =

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-14T04:44:58.307960Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers