Layer-Aware Representation Filtering: Purifying Finetuning Data to Preserve LLM Safety Alignment | Paper Citation Record

Observation 853d5b88-5b37-4838-8b8d-3928eb6c2755 · outbound

This paper cites online" 'onlinestring :=.

Layer-Aware Representation Filtering: Purifying Finetuning Data to Preserve LLM Safety Alignment online" 'onlinestring :=

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-15T18:13:58.063350Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c4ea7ce4-9aba-42c9-b50b-17e999d18e22 · outbound

This paper cites write newline.

Layer-Aware Representation Filtering: Purifying Finetuning Data to Preserve LLM Safety Alignment write newline

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-15T18:13:58.068887Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f8963a37-f4d4-4fe0-a1fe-642bb77782a8 · outbound

This paper cites Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone.

Layer-Aware Representation Filtering: Purifying Finetuning Data to Preserve LLM Safety Alignment Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-15T18:13:58.073741Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0feb4913-2f92-4f62-b2a4-f21cdc343e30 · outbound

This paper cites an unresolved cited work.

Layer-Aware Representation Filtering: Purifying Finetuning Data to Preserve LLM Safety Alignment Unresolved cited work

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-15T18:13:58.079059Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 34d717fb-f455-4513-98da-761d3975516e · outbound

This paper cites Evaluating Large Language Models Trained on Code.

Layer-Aware Representation Filtering: Purifying Finetuning Data to Preserve LLM Safety Alignment Evaluating Large Language Models Trained on Code

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-15T18:13:58.083669Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 95f71dd0-a009-47e1-9b09-0a6ea0771e2b · outbound

This paper cites an unresolved cited work.

Layer-Aware Representation Filtering: Purifying Finetuning Data to Preserve LLM Safety Alignment Unresolved cited work

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-15T18:13:58.087943Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eb39f237-eb76-4b3e-9b9e-f641630cc130 · outbound

This paper cites an unresolved cited work.

Layer-Aware Representation Filtering: Purifying Finetuning Data to Preserve LLM Safety Alignment Unresolved cited work

Reference 7

Resolution: unresolved; raw_fallback, observed 2026-08-15T18:13:59.351858Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation d108daec-9c67-4b2a-95f9-5488ec0d0216 · outbound

This paper cites Toward Secure Tuning: Mitigating Security Risks from Instruction Fine-Tuning.

Layer-Aware Representation Filtering: Purifying Finetuning Data to Preserve LLM Safety Alignment Toward Secure Tuning: Mitigating Security Risks from Instruction Fine-Tuning

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-15T18:13:58.096730Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b0cb59f1-cc2b-48e8-9ece-a4a3dd1880a4 · outbound

This paper cites Safeguard Fine-Tuned LLMs Through Pre- and Post-Tuning Model Merging.

Layer-Aware Representation Filtering: Purifying Finetuning Data to Preserve LLM Safety Alignment Safeguard Fine-Tuned LLMs Through Pre- and Post-Tuning Model Merging

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-15T18:13:58.102071Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eab81e58-646d-4830-9ef8-64a26358ae24 · outbound

This paper cites an unresolved cited work.

Layer-Aware Representation Filtering: Purifying Finetuning Data to Preserve LLM Safety Alignment Unresolved cited work

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-15T18:13:58.107373Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3ec54ef0-dfa6-463a-a861-6c37894113b3 · outbound

This paper cites an unresolved cited work.

Layer-Aware Representation Filtering: Purifying Finetuning Data to Preserve LLM Safety Alignment Unresolved cited work

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-15T18:13:58.113830Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 21ffb058-7435-4eee-b72a-03113c0aa761 · outbound

This paper cites an unresolved cited work.

Layer-Aware Representation Filtering: Purifying Finetuning Data to Preserve LLM Safety Alignment Unresolved cited work

Reference 12

Resolution: unresolved; raw_fallback, observed 2026-08-15T18:13:59.330442Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 3e89adbe-4c88-49a1-a2a2-dbf903111736 · outbound

This paper cites an unresolved cited work.

Layer-Aware Representation Filtering: Purifying Finetuning Data to Preserve LLM Safety Alignment Unresolved cited work

Reference 13

Resolution: unresolved; raw_fallback, observed 2026-08-15T18:13:59.317624Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 6f82fae8-639f-4c48-80c1-85495d458c34 · outbound

This paper cites an unresolved cited work.

Layer-Aware Representation Filtering: Purifying Finetuning Data to Preserve LLM Safety Alignment Unresolved cited work

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-15T18:13:58.126797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 31ccae20-a47e-4daa-b67b-a85a597e9050 · outbound

This paper cites an unresolved cited work.

Layer-Aware Representation Filtering: Purifying Finetuning Data to Preserve LLM Safety Alignment Unresolved cited work

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-15T18:13:58.130907Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 184995cf-ca86-4440-a72a-559a7f391ea4 · outbound

This paper cites VLSBench: Unveiling Visual Leakage in Multimodal Safety.

Layer-Aware Representation Filtering: Purifying Finetuning Data to Preserve LLM Safety Alignment VLSBench: Unveiling Visual Leakage in Multimodal Safety

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-15T18:13:58.134740Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bd18d47d-7abf-4508-898c-8623a8408cbe · outbound

This paper cites Harmful Fine-tuning Attacks and Defenses for Large Language Models: A Survey.

Layer-Aware Representation Filtering: Purifying Finetuning Data to Preserve LLM Safety Alignment Harmful Fine-tuning Attacks and Defenses for Large Language Models: A Survey

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-15T18:13:58.138769Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 73f76105-b10d-4c98-9208-e362b0c12fcd · outbound

This paper cites an unresolved cited work.

Layer-Aware Representation Filtering: Purifying Finetuning Data to Preserve LLM Safety Alignment Unresolved cited work

Reference 18

Resolution: unresolved; raw_fallback, observed 2026-08-15T18:13:59.287956Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 3de25048-435c-4f7c-883c-9b4a34220732 · outbound

This paper cites Mistral 7B.

Layer-Aware Representation Filtering: Purifying Finetuning Data to Preserve LLM Safety Alignment Mistral 7B

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-15T18:13:58.147434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e0600772-ae63-4681-a634-df59de2a1b78 · outbound

This paper cites PubMedQA: A Dataset for Biomedical Research Question Answering.

Layer-Aware Representation Filtering: Purifying Finetuning Data to Preserve LLM Safety Alignment PubMedQA: A Dataset for Biomedical Research Question Answering

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-15T18:13:58.151662Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0525ec50-605a-4d1a-a707-e5adc41d6dce · outbound

This paper cites an unresolved cited work.

Layer-Aware Representation Filtering: Purifying Finetuning Data to Preserve LLM Safety Alignment Unresolved cited work

Reference 21

Resolution: unresolved; raw_fallback, observed 2026-08-15T18:13:59.274830Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 1f89ed07-990b-4cfc-8f93-ba7549c2b795 · outbound

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

Layer-Aware Representation Filtering: Purifying Finetuning Data to Preserve LLM Safety Alignment SALAD-Bench: A Hierarchical and Comprehensive Safety Benchmark for Large Language Models

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-15T18:13:58.160012Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 155e2823-2219-4059-b2ed-1ce90deb75d9 · outbound

This paper cites an unresolved cited work.

Layer-Aware Representation Filtering: Purifying Finetuning Data to Preserve LLM Safety Alignment Unresolved cited work

Reference 23

Resolution: unresolved; raw_fallback, observed 2026-08-15T18:13:59.261019Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 1827fb46-584a-4792-9e48-80aa1a195127 · outbound

This paper cites an unresolved cited work.

Layer-Aware Representation Filtering: Purifying Finetuning Data to Preserve LLM Safety Alignment Unresolved cited work

Reference 24

Resolution: unresolved; raw_fallback, observed 2026-08-15T18:13:59.248134Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 67c4c9a9-cb02-4d1c-ac31-595be8e96163 · outbound

This paper cites an unresolved cited work.

Layer-Aware Representation Filtering: Purifying Finetuning Data to Preserve LLM Safety Alignment Unresolved cited work

Reference 25

Resolution: unresolved; raw_fallback, observed 2026-08-15T18:13:59.234462Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation ef3e8b43-1d09-417c-92bd-386a0cc1f3b2 · outbound

This paper cites The Llama 3 Herd of Models.

Layer-Aware Representation Filtering: Purifying Finetuning Data to Preserve LLM Safety Alignment The Llama 3 Herd of Models

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-15T18:13:58.176161Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0ccec216-7161-42f3-8662-6d52a06b04c7 · outbound

This paper cites Le, Barret Zoph, Jason Wei, and Adam Roberts.

Layer-Aware Representation Filtering: Purifying Finetuning Data to Preserve LLM Safety Alignment Le, Barret Zoph, Jason Wei, and Adam Roberts

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:13:59.221218Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 63b3335f-14ac-4fd6-b0a2-446ee4ea9f79 · outbound

This paper cites an unresolved cited work.

Layer-Aware Representation Filtering: Purifying Finetuning Data to Preserve LLM Safety Alignment Unresolved cited work

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-15T18:13:58.185761Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 92a0e61a-e8a1-4e22-a4f0-894b0f6f7b7c · outbound

This paper cites an unresolved cited work.

Layer-Aware Representation Filtering: Purifying Finetuning Data to Preserve LLM Safety Alignment Unresolved cited work

Reference 29

Resolution: unresolved; raw_fallback, observed 2026-08-15T18:13:59.207039Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation f901c20c-96aa-45b4-b63b-0e2b2411d0a8 · outbound

This paper cites an unresolved cited work.

Layer-Aware Representation Filtering: Purifying Finetuning Data to Preserve LLM Safety Alignment Unresolved cited work

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-15T18:13:58.193740Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 14f144ce-bfac-4c26-a57e-291a99e6f821 · outbound

This paper cites HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal.

Layer-Aware Representation Filtering: Purifying Finetuning Data to Preserve LLM Safety Alignment HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-15T18:13:58.197941Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4a5a84a6-a340-46a4-8c79-755e0cf8f018 · outbound

This paper cites an unresolved cited work.

Layer-Aware Representation Filtering: Purifying Finetuning Data to Preserve LLM Safety Alignment Unresolved cited work

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-15T18:13:58.202174Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bc8e3bf2-20bd-495b-b762-f8539d6ebb80 · outbound

This paper cites Orca: Progressive Learning from Complex Explanation Traces of GPT-4.

Layer-Aware Representation Filtering: Purifying Finetuning Data to Preserve LLM Safety Alignment Orca: Progressive Learning from Complex Explanation Traces of GPT-4

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-15T18:13:58.206597Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7ec92b30-77f1-4820-b4c2-2cdb605dc7f3 · outbound

This paper cites The Hidden Dimensions of LLM Alignment: A Multi-Dimensional Analysis of Orthogonal Safety Directions.

Layer-Aware Representation Filtering: Purifying Finetuning Data to Preserve LLM Safety Alignment The Hidden Dimensions of LLM Alignment: A Multi-Dimensional Analysis of Orthogonal Safety Directions

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-15T18:13:58.211236Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 963cd09d-a9a1-409b-a56d-39695c76b58e · outbound

This paper cites an unresolved cited work.

Layer-Aware Representation Filtering: Purifying Finetuning Data to Preserve LLM Safety Alignment Unresolved cited work

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-15T18:13:58.216544Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 171f5cbf-5b79-4229-aa8b-5396ee8de8bf · outbound

This paper cites Instruction Tuning with GPT-4.

Layer-Aware Representation Filtering: Purifying Finetuning Data to Preserve LLM Safety Alignment Instruction Tuning with GPT-4

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-15T18:13:58.220450Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 96781a24-793d-4aca-b356-404b7ec5096d · outbound

This paper cites an unresolved cited work.

Layer-Aware Representation Filtering: Purifying Finetuning Data to Preserve LLM Safety Alignment Unresolved cited work

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-15T18:13:58.224735Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ab883154-8edd-4b91-a4b1-73af5c88e90a · outbound

This paper cites an unresolved cited work.

Layer-Aware Representation Filtering: Purifying Finetuning Data to Preserve LLM Safety Alignment Unresolved cited work

Reference 38

Resolution: unresolved; raw_fallback, observed 2026-08-15T18:13:59.177364Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 451dedea-7b0b-4cc8-9c59-e863dfd9534a · outbound

This paper cites Qwen2.5 Technical Report.

Layer-Aware Representation Filtering: Purifying Finetuning Data to Preserve LLM Safety Alignment Qwen2.5 Technical Report

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-15T18:13:58.232479Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d49d37f8-03e6-4018-8feb-6f349ab08c85 · outbound

This paper cites an unresolved cited work.

Layer-Aware Representation Filtering: Purifying Finetuning Data to Preserve LLM Safety Alignment Unresolved cited work

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-15T18:13:58.236321Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2888ba6a-04df-4405-b813-0250bd762f94 · outbound

This paper cites an unresolved cited work.

Layer-Aware Representation Filtering: Purifying Finetuning Data to Preserve LLM Safety Alignment Unresolved cited work

Reference 41

Resolution: unresolved; raw_fallback, observed 2026-08-15T18:13:59.164425Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 564797de-c99d-4454-b729-85aa6e7e69ba · outbound

This paper cites an unresolved cited work.

Layer-Aware Representation Filtering: Purifying Finetuning Data to Preserve LLM Safety Alignment Unresolved cited work

Reference 42

Resolution: unresolved; raw_fallback, observed 2026-08-15T18:13:59.150561Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 5e4944a2-8146-4fa9-bc7e-422ed32d7d06 · outbound

This paper cites an unresolved cited work.

Layer-Aware Representation Filtering: Purifying Finetuning Data to Preserve LLM Safety Alignment Unresolved cited work

Reference 43

Resolution: unresolved; raw_fallback, observed 2026-08-15T18:13:59.137665Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation fb90d4b0-da16-44bc-bb0f-d2074f7446a6 · outbound

This paper cites Hashimoto.

Layer-Aware Representation Filtering: Purifying Finetuning Data to Preserve LLM Safety Alignment Hashimoto

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-15T18:13:58.252634Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 72a653c1-e72f-4547-8f1a-fbec0a5d1d4f · outbound

This paper cites an unresolved cited work.

Layer-Aware Representation Filtering: Purifying Finetuning Data to Preserve LLM Safety Alignment Unresolved cited work

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-15T18:13:58.256725Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 53369d06-f6a7-46af-a47e-8343964a5297 · outbound

This paper cites DiffusionAttacker: Diffusion-Driven Prompt Manipulation for LLM Jailbreak.

Layer-Aware Representation Filtering: Purifying Finetuning Data to Preserve LLM Safety Alignment DiffusionAttacker: Diffusion-Driven Prompt Manipulation for LLM Jailbreak

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-15T18:13:58.260498Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 59a330a3-7630-4926-a78e-eb2d59ded940 · outbound

This paper cites an unresolved cited work.

Layer-Aware Representation Filtering: Purifying Finetuning Data to Preserve LLM Safety Alignment Unresolved cited work

Reference 47

Resolution: unresolved; raw_fallback, observed 2026-08-15T18:13:59.107927Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation f04d4964-7648-41d6-8fcc-161f0321a0db · outbound

This paper cites BloombergGPT: A Large Language Model for Finance.

Layer-Aware Representation Filtering: Purifying Finetuning Data to Preserve LLM Safety Alignment BloombergGPT: A Large Language Model for Finance

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-15T18:13:58.269384Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f7aec56e-9a6d-4a00-a148-0ec82b4c2fd5 · outbound

This paper cites an unresolved cited work.

Layer-Aware Representation Filtering: Purifying Finetuning Data to Preserve LLM Safety Alignment Unresolved cited work

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-15T18:13:58.273453Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 06b08e16-65e4-416d-9cca-039eeb1a402e · outbound

This paper cites an unresolved cited work.

Layer-Aware Representation Filtering: Purifying Finetuning Data to Preserve LLM Safety Alignment Unresolved cited work

Reference 50

Resolution: unresolved; raw_fallback, observed 2026-08-15T18:13:59.086526Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 6ad2df5b-c7ae-4824-9c5c-3e0207162186 · outbound

This paper cites MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models.

Layer-Aware Representation Filtering: Purifying Finetuning Data to Preserve LLM Safety Alignment MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-15T18:13:58.282824Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c22a5ecc-d184-4848-8f80-e37a9ff148b5 · outbound

This paper cites an unresolved cited work.

Layer-Aware Representation Filtering: Purifying Finetuning Data to Preserve LLM Safety Alignment Unresolved cited work

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-15T18:13:58.287060Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 500277c0-7578-402f-91d5-72864343f2d5 · outbound

This paper cites an unresolved cited work.

Layer-Aware Representation Filtering: Purifying Finetuning Data to Preserve LLM Safety Alignment Unresolved cited work

Reference 53

Resolution: unresolved; raw_fallback, observed 2026-08-15T18:13:59.073501Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 448351e1-35eb-436c-8526-e03f6041d412 · outbound

This paper cites an unresolved cited work.

Layer-Aware Representation Filtering: Purifying Finetuning Data to Preserve LLM Safety Alignment Unresolved cited work

Reference 54

Resolution: unresolved; raw_fallback, observed 2026-08-15T18:13:59.059765Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 9801f925-faa7-4bbf-8d7b-df8ab9294fd2 · outbound

This paper cites an unresolved cited work.

Layer-Aware Representation Filtering: Purifying Finetuning Data to Preserve LLM Safety Alignment Unresolved cited work

Reference 55

Resolution: unresolved; raw_fallback, observed 2026-08-15T18:13:59.045166Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 2f1efd34-6d5b-4aef-998c-1c6f65924b32 · outbound

This paper cites EasyJailbreak: A Unified Framework for Jailbreaking Large Language Models.

Layer-Aware Representation Filtering: Purifying Finetuning Data to Preserve LLM Safety Alignment EasyJailbreak: A Unified Framework for Jailbreaking Large Language Models

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-15T18:13:58.303164Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4c70829f-df76-4c64-aee7-e9700c6203d7 · outbound

This paper cites Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models.

Layer-Aware Representation Filtering: Purifying Finetuning Data to Preserve LLM Safety Alignment Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-15T18:13:58.308125Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 172b5635-ec66-430d-811f-7942b5821db1 · outbound

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

Layer-Aware Representation Filtering: Purifying Finetuning Data to Preserve LLM Safety Alignment Representation Engineering: A Top-Down Approach to AI Transparency

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-15T18:13:58.312212Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 123f864d-d679-420f-b0a0-ce10dd35ac5d · outbound

This paper cites Improving Alignment and Robustness with Circuit Breakers.

Layer-Aware Representation Filtering: Purifying Finetuning Data to Preserve LLM Safety Alignment Improving Alignment and Robustness with Circuit Breakers

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-15T18:13:58.316618Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0fb29fb7-df3b-42eb-953d-146c7be5fd32 · outbound

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

Layer-Aware Representation Filtering: Purifying Finetuning Data to Preserve LLM Safety Alignment Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-15T18:13:58.320855Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers