PRM-Free Security Alignment of Large Models via Red Teaming and Adversarial Training | Paper Citation Record

Observation 5b6a9238-00de-4972-a6c5-c256e98d095c · outbound

This paper cites online" 'onlinestring :=.

PRM-Free Security Alignment of Large Models via Red Teaming and Adversarial Training online" 'onlinestring :=

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-06T17:35:47.238850Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 25cf31f4-6c6d-409f-b5cb-f7b395d031a2 · outbound

This paper cites write newline.

PRM-Free Security Alignment of Large Models via Red Teaming and Adversarial Training write newline

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-06T17:35:47.390160Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5a2af6a0-2e86-4504-8cbc-6ffeed6a1cde · outbound

This paper cites an unresolved cited work.

PRM-Free Security Alignment of Large Models via Red Teaming and Adversarial Training Unresolved cited work

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-06T17:35:47.424574Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bb252c79-5804-47f0-aa0b-2b0227ac2c84 · outbound

This paper cites Generating Natural Language Adversarial Examples.

PRM-Free Security Alignment of Large Models via Red Teaming and Adversarial Training Generating Natural Language Adversarial Examples

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-06T17:35:47.437181Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ffcb86b7-123f-42ce-8130-0269d61955ec · outbound

This paper cites A General Language Assistant as a Laboratory for Alignment.

PRM-Free Security Alignment of Large Models via Red Teaming and Adversarial Training A General Language Assistant as a Laboratory for Alignment

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-06T17:35:47.468119Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation adcb3d4e-4952-4233-a7a6-2fef21cd219c · outbound

This paper cites Spinning Language Models: Risks of Propaganda-As-A-Service and Countermeasures.

PRM-Free Security Alignment of Large Models via Red Teaming and Adversarial Training Spinning Language Models: Risks of Propaganda-As-A-Service and Countermeasures

Reference 6

Resolution: verified exact; local_arxiv, observed 2026-08-06T17:35:50.534543Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 1f8b8625-ea52-45ea-9324-d027089e80ba · outbound

This paper cites Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback.

PRM-Free Security Alignment of Large Models via Red Teaming and Adversarial Training Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-06T17:35:47.608128Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b29ff979-9448-4e35-8bf3-47d149d4744a · outbound

This paper cites Constitutional AI: Harmlessness from AI Feedback.

PRM-Free Security Alignment of Large Models via Red Teaming and Adversarial Training Constitutional AI: Harmlessness from AI Feedback

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-06T17:35:47.723342Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 517e308b-7e38-4685-85ce-e9f649f6d4c3 · outbound

This paper cites Image Hijacks: Adversarial Images can Control Generative Models at Runtime.

PRM-Free Security Alignment of Large Models via Red Teaming and Adversarial Training Image Hijacks: Adversarial Images can Control Generative Models at Runtime

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-06T17:35:47.822419Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d51cbcab-b7d2-41ed-9e8c-b1dc9bbbc282 · outbound

This paper cites an unresolved cited work.

PRM-Free Security Alignment of Large Models via Red Teaming and Adversarial Training Unresolved cited work

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-06T17:35:47.897090Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8202b0ae-a407-4800-8fcc-ad004b22a9d0 · outbound

This paper cites an unresolved cited work.

PRM-Free Security Alignment of Large Models via Red Teaming and Adversarial Training Unresolved cited work

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-06T17:35:47.960711Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 21677c54-689c-4f87-803a-53f3d739d648 · outbound

This paper cites an unresolved cited work.

PRM-Free Security Alignment of Large Models via Red Teaming and Adversarial Training Unresolved cited work

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-06T17:35:47.970414Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ce3d1067-2d5b-4af6-bd46-b95bde12f133 · outbound

This paper cites On the Opportunities and Risks of Foundation Models.

PRM-Free Security Alignment of Large Models via Red Teaming and Adversarial Training On the Opportunities and Risks of Foundation Models

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-06T17:35:47.975977Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bafa7bb3-a8c0-48c3-884f-7ca91f77b74e · outbound

This paper cites Evaluating the Susceptibility of Pre-Trained Language Models via Handcrafted Adversarial Examples.

PRM-Free Security Alignment of Large Models via Red Teaming and Adversarial Training Evaluating the Susceptibility of Pre-Trained Language Models via Handcrafted Adversarial Examples

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-06T17:35:47.982288Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b26876fb-8ead-4a31-9765-0039acb31008 · outbound

This paper cites an unresolved cited work.

PRM-Free Security Alignment of Large Models via Red Teaming and Adversarial Training Unresolved cited work

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-06T17:35:47.989197Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4bb4e62a-f278-4460-86c3-e2119a30d3e8 · outbound

This paper cites an unresolved cited work.

PRM-Free Security Alignment of Large Models via Red Teaming and Adversarial Training Unresolved cited work

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-06T17:35:47.996109Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8a5a0256-0ed2-4a11-a324-0a6ae5dfe732 · outbound

This paper cites Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback.

PRM-Free Security Alignment of Large Models via Red Teaming and Adversarial Training Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-06T17:35:48.002781Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ee47c9ff-dcb0-43a9-a097-9fad4e0e75d8 · outbound

This paper cites Explore, Establish, Exploit: Red Teaming Language Models from Scratch.

PRM-Free Security Alignment of Large Models via Red Teaming and Adversarial Training Explore, Establish, Exploit: Red Teaming Language Models from Scratch

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-06T17:35:48.010807Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4fd144ea-56ba-462c-b157-c2c2fccc610b · outbound

This paper cites Jailbreaking Black Box Large Language Models in Twenty Queries.

PRM-Free Security Alignment of Large Models via Red Teaming and Adversarial Training Jailbreaking Black Box Large Language Models in Twenty Queries

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-06T17:35:48.018055Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2f3b1b5c-6c78-4d68-a448-028cd001b60f · outbound

This paper cites an unresolved cited work.

PRM-Free Security Alignment of Large Models via Red Teaming and Adversarial Training Unresolved cited work

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-06T17:35:48.025371Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 670b6015-0d51-4533-b7e0-7978b003fe56 · outbound

This paper cites Evaluating Large Language Models Trained on Code.

PRM-Free Security Alignment of Large Models via Red Teaming and Adversarial Training Evaluating Large Language Models Trained on Code

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-06T17:35:48.035926Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3aa09c3e-12c8-4063-9d99-bb9690b6accf · outbound

This paper cites PaLM: Scaling Language Modeling with Pathways.

PRM-Free Security Alignment of Large Models via Red Teaming and Adversarial Training PaLM: Scaling Language Modeling with Pathways

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-06T17:35:48.042843Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3d70f730-9dc9-4af2-bf75-7a0924bd6251 · outbound

This paper cites an unresolved cited work.

PRM-Free Security Alignment of Large Models via Red Teaming and Adversarial Training Unresolved cited work

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-06T17:35:48.053465Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a11d8663-aa43-4de8-bd1e-a858946f0824 · outbound

This paper cites Supervising strong learners by amplifying weak experts.

PRM-Free Security Alignment of Large Models via Red Teaming and Adversarial Training Supervising strong learners by amplifying weak experts

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-06T17:35:48.063524Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9f0d440a-ef33-4ceb-9f85-df8526eb4c94 · outbound

This paper cites an unresolved cited work.

PRM-Free Security Alignment of Large Models via Red Teaming and Adversarial Training Unresolved cited work

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-06T17:35:48.070951Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c904d3f8-3630-4b9d-8b71-f52597e821f0 · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

PRM-Free Security Alignment of Large Models via Red Teaming and Adversarial Training Training Verifiers to Solve Math Word Problems

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-06T17:35:48.078087Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d6639d9f-321d-44b7-ab7f-ad5bad9c5d6b · outbound

This paper cites Multilingual Jailbreak Challenges in Large Language Models.

PRM-Free Security Alignment of Large Models via Red Teaming and Adversarial Training Multilingual Jailbreak Challenges in Large Language Models

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-06T17:35:48.084454Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 68c61a06-cfae-48e7-abb9-2bb1571c8feb · outbound

This paper cites an unresolved cited work.

PRM-Free Security Alignment of Large Models via Red Teaming and Adversarial Training Unresolved cited work

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-06T17:35:48.092363Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9acddfb3-9cda-4059-94d5-cd8bd0434b18 · outbound

This paper cites Understanding parameter differences between analyses employing nested data subsets.

PRM-Free Security Alignment of Large Models via Red Teaming and Adversarial Training Understanding parameter differences between analyses employing nested data subsets

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-06T17:35:48.100821Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7f34939f-ae70-482c-8392-47ddccbdb6f8 · outbound

This paper cites an unresolved cited work.

PRM-Free Security Alignment of Large Models via Red Teaming and Adversarial Training Unresolved cited work

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-06T17:35:48.109664Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 26c25ec9-a7aa-48cb-96d2-11d2f2c0cce6 · outbound

This paper cites HotFlip: White-Box Adversarial Examples for Text Classification.

PRM-Free Security Alignment of Large Models via Red Teaming and Adversarial Training HotFlip: White-Box Adversarial Examples for Text Classification

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-06T17:35:48.119501Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3f696111-d4ca-4c96-85f0-7d428d2af8ab · outbound

This paper cites an unresolved cited work.

PRM-Free Security Alignment of Large Models via Red Teaming and Adversarial Training Unresolved cited work

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-06T17:35:48.128310Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c42d8818-3e1d-410f-87ba-4fa7f898a85c · outbound

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

PRM-Free Security Alignment of Large Models via Red Teaming and Adversarial Training Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-06T17:35:48.134541Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ce2fcbd-d0d9-4e9e-9491-0c12d0b58c02 · outbound

This paper cites Scaling Laws for Reward Model Overoptimization.

PRM-Free Security Alignment of Large Models via Red Teaming and Adversarial Training Scaling Laws for Reward Model Overoptimization

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-06T17:35:48.142756Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a90ddecf-99c1-405b-be46-b442ad14d8ed · outbound

This paper cites RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models.

PRM-Free Security Alignment of Large Models via Red Teaming and Adversarial Training RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-06T17:35:48.151517Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ebcc7130-ae12-485b-8d12-beb2658a661d · outbound

This paper cites Explaining and Harnessing Adversarial Examples.

PRM-Free Security Alignment of Large Models via Red Teaming and Adversarial Training Explaining and Harnessing Adversarial Examples

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-06T17:35:48.158428Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b94e92c5-e06a-46e3-8ddb-3c4b945c6be3 · outbound

This paper cites Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection.

PRM-Free Security Alignment of Large Models via Red Teaming and Adversarial Training Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-06T17:35:48.166666Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 590e6d0d-c3b9-4aa1-91cb-f62b13467cb5 · outbound

This paper cites an unresolved cited work.

PRM-Free Security Alignment of Large Models via Red Teaming and Adversarial Training Unresolved cited work

Reference 39

Resolution: unresolved; raw_fallback, observed 2026-08-06T17:35:50.981468Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 0358867b-52e6-45ba-b59c-97ede6e52fe3 · outbound

This paper cites Measuring Massive Multitask Language Understanding.

PRM-Free Security Alignment of Large Models via Red Teaming and Adversarial Training Measuring Massive Multitask Language Understanding

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-06T17:35:48.184013Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 28085756-3d06-4400-9799-143a92401037 · outbound

This paper cites Training Compute-Optimal Large Language Models.

PRM-Free Security Alignment of Large Models via Red Teaming and Adversarial Training Training Compute-Optimal Large Language Models

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-06T17:35:48.190750Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6df30fc5-7a42-4e0a-883e-420551bc9683 · outbound

This paper cites AI safety via debate.

PRM-Free Security Alignment of Large Models via Red Teaming and Adversarial Training AI safety via debate

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-06T17:35:48.198213Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c3918a90-c15b-44a3-8567-3f9d1bed0a53 · outbound

This paper cites an unresolved cited work.

PRM-Free Security Alignment of Large Models via Red Teaming and Adversarial Training Unresolved cited work

Reference 43

Resolution: unresolved; raw_fallback, observed 2026-08-06T17:35:50.954180Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 8e4b1b4f-1cda-4008-9ac4-a6828bb2fbb5 · outbound

This paper cites an unresolved cited work.

PRM-Free Security Alignment of Large Models via Red Teaming and Adversarial Training Unresolved cited work

Reference 44

Resolution: unresolved; raw_fallback, observed 2026-08-06T17:35:50.925417Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 8483a57a-aedc-4071-8651-da0a3aacd10c · outbound

This paper cites an unresolved cited work.

PRM-Free Security Alignment of Large Models via Red Teaming and Adversarial Training Unresolved cited work

Reference 45

Resolution: unresolved; raw_fallback, observed 2026-08-06T17:35:50.898671Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 72828130-3626-46ec-aaa7-9b4442706d5a · outbound

This paper cites Automatically Auditing Large Language Models via Discrete Optimization.

PRM-Free Security Alignment of Large Models via Red Teaming and Adversarial Training Automatically Auditing Large Language Models via Discrete Optimization

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-06T17:35:48.231633Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c5bdc0bf-891b-4c3d-9cf6-b5b29d6825b6 · outbound

This paper cites Single-Source Shortest Paths with Negative Real Weights in $\tilde{O}(mn^{8/9})$ Time.

PRM-Free Security Alignment of Large Models via Red Teaming and Adversarial Training Single-Source Shortest Paths with Negative Real Weights in $\tilde{O}(mn^{8/9})$ Time

Reference 47

Resolution: verified exact; local_arxiv, observed 2026-08-06T17:35:49.762344Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 8e39d5a0-df53-4a41-813c-fd6d04b2881a · outbound

This paper cites Open Sesame! Universal Black Box Jailbreaking of Large Language Models.

PRM-Free Security Alignment of Large Models via Red Teaming and Adversarial Training Open Sesame! Universal Black Box Jailbreaking of Large Language Models

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-06T17:35:48.251121Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6893840f-8913-456c-8bfe-03992331d013 · outbound

This paper cites Scalable agent alignment via reward modeling: a research direction.

PRM-Free Security Alignment of Large Models via Red Teaming and Adversarial Training Scalable agent alignment via reward modeling: a research direction

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-06T17:35:48.260173Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c2709b8d-4f65-4d21-ab92-6b9473858fa6 · outbound

This paper cites BERT-ATTACK: Adversarial Attack Against BERT Using BERT.

PRM-Free Security Alignment of Large Models via Red Teaming and Adversarial Training BERT-ATTACK: Adversarial Attack Against BERT Using BERT

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-06T17:35:48.267389Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dd64e832-2a45-4da9-bb99-41539ed0ca24 · outbound

This paper cites Let's Verify Step by Step.

PRM-Free Security Alignment of Large Models via Red Teaming and Adversarial Training Let's Verify Step by Step

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-06T17:35:48.273778Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b907c4eb-d916-4cbd-8fa8-60a699c361d2 · outbound

This paper cites Jailbreaking ChatGPT via Prompt Engineering: An Empirical Study.

PRM-Free Security Alignment of Large Models via Red Teaming and Adversarial Training Jailbreaking ChatGPT via Prompt Engineering: An Empirical Study

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-06T17:35:48.280960Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 67ea4d27-d6a9-4d67-a875-6c9bd7c3dada · outbound

This paper cites an unresolved cited work.

PRM-Free Security Alignment of Large Models via Red Teaming and Adversarial Training Unresolved cited work

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-06T17:35:48.289162Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c8382987-8b29-4efe-b8c6-1a8ea5283f86 · outbound

This paper cites Towards Deep Learning Models Resistant to Adversarial Attacks.

PRM-Free Security Alignment of Large Models via Red Teaming and Adversarial Training Towards Deep Learning Models Resistant to Adversarial Attacks

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-06T17:35:48.302663Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 455d04b7-778b-4caa-897a-b06d86de4b1b · outbound

This paper cites an unresolved cited work.

PRM-Free Security Alignment of Large Models via Red Teaming and Adversarial Training Unresolved cited work

Reference 55

Resolution: unresolved; raw_fallback, observed 2026-08-06T17:35:50.871578Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 53fcdf3a-c28f-4d2c-89ca-8008a48a9534 · outbound

This paper cites Tree of Attacks: Jailbreaking Black-Box LLMs Automatically.

PRM-Free Security Alignment of Large Models via Red Teaming and Adversarial Training Tree of Attacks: Jailbreaking Black-Box LLMs Automatically

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-06T17:35:48.318958Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 77b7dbcc-5efa-42cb-92e5-75aeb0e2ccae · outbound

This paper cites Teaching language models to support answers with verified quotes.

PRM-Free Security Alignment of Large Models via Red Teaming and Adversarial Training Teaching language models to support answers with verified quotes

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-06T17:35:48.325823Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 55775cee-9169-4500-90d2-4eb9a2b99214 · outbound

This paper cites an unresolved cited work.

PRM-Free Security Alignment of Large Models via Red Teaming and Adversarial Training Unresolved cited work

Reference 58

Resolution: unresolved; raw_fallback, observed 2026-08-06T17:35:50.842475Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation f5cccaa2-679e-4f61-81c4-4e13dd8d6e5f · outbound

This paper cites an unresolved cited work.

PRM-Free Security Alignment of Large Models via Red Teaming and Adversarial Training Unresolved cited work

Reference 59

Resolution: unresolved; raw_fallback, observed 2026-08-06T17:35:50.813928Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 103ae790-ec3e-4edf-bf4e-122cf26e8719 · outbound

This paper cites TextAttack: A Framework for Adversarial Attacks, Data Augmentation, and Adversarial Training in NLP.

PRM-Free Security Alignment of Large Models via Red Teaming and Adversarial Training TextAttack: A Framework for Adversarial Attacks, Data Augmentation, and Adversarial Training in NLP

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-06T17:35:48.347629Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 482fea23-f239-4910-9841-c2975ba97d87 · outbound

This paper cites WebGPT: Browser-assisted question-answering with human feedback.

PRM-Free Security Alignment of Large Models via Red Teaming and Adversarial Training WebGPT: Browser-assisted question-answering with human feedback

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-06T17:35:48.355471Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a701af0a-b1cc-4a10-8629-972734d4f80b · outbound

This paper cites Scalable Extraction of Training Data from (Production) Language Models.

PRM-Free Security Alignment of Large Models via Red Teaming and Adversarial Training Scalable Extraction of Training Data from (Production) Language Models

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-06T17:35:48.362446Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 569713c6-6f4f-406f-9e2d-46aca8eaa3e5 · outbound

This paper cites an unresolved cited work.

PRM-Free Security Alignment of Large Models via Red Teaming and Adversarial Training Unresolved cited work

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-06T17:35:48.370906Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 206bfffb-3393-4296-b8ed-1a4e1c1631e4 · outbound

This paper cites Red Teaming Language Models with Language Models.

PRM-Free Security Alignment of Large Models via Red Teaming and Adversarial Training Red Teaming Language Models with Language Models

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-06T17:35:48.379195Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1811695b-06f0-464a-b606-483a2f9e0eb1 · outbound

This paper cites Discovering Language Model Behaviors with Model-Written Evaluations.

PRM-Free Security Alignment of Large Models via Red Teaming and Adversarial Training Discovering Language Model Behaviors with Model-Written Evaluations

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-06T17:35:48.387140Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3b8e7847-6a86-4fb4-8f3c-f5a359046bd3 · outbound

This paper cites Ignore Previous Prompt: Attack Techniques For Language Models.

PRM-Free Security Alignment of Large Models via Red Teaming and Adversarial Training Ignore Previous Prompt: Attack Techniques For Language Models

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-06T17:35:48.395357Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 83499b1b-c548-4c87-9a07-9c519391f9b0 · outbound

This paper cites an unresolved cited work.

PRM-Free Security Alignment of Large Models via Red Teaming and Adversarial Training Unresolved cited work

Reference 67

Resolution: unresolved; raw_fallback, observed 2026-08-06T17:35:50.775043Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 3fb3cb18-7a56-41ee-aad5-997006c0baf9 · outbound

This paper cites Adversarial Training Can Hurt Generalization.

PRM-Free Security Alignment of Large Models via Red Teaming and Adversarial Training Adversarial Training Can Hurt Generalization

Reference 68

Resolution: unresolved; no resolver link, observed 2026-08-06T17:35:48.413261Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 453ce8c0-9e8e-4e86-8651-b26a2615ab74 · outbound

This paper cites an unresolved cited work.

PRM-Free Security Alignment of Large Models via Red Teaming and Adversarial Training Unresolved cited work

Reference 69

Resolution: unresolved; raw_fallback, observed 2026-08-06T17:35:50.752692Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation f1664621-df1b-4744-89eb-98e8f0ef31ba · outbound

This paper cites Proximal Policy Optimization Algorithms.

PRM-Free Security Alignment of Large Models via Red Teaming and Adversarial Training Proximal Policy Optimization Algorithms

Reference 70

Resolution: unresolved; no resolver link, observed 2026-08-06T17:35:48.427520Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b853babb-024f-485f-bda8-0d6e9d553ba5 · outbound

This paper cites Scalable and Transferable Black-Box Jailbreaks for Language Models via Persona Modulation.

PRM-Free Security Alignment of Large Models via Red Teaming and Adversarial Training Scalable and Transferable Black-Box Jailbreaks for Language Models via Persona Modulation

Reference 71

Resolution: unresolved; no resolver link, observed 2026-08-06T17:35:48.436360Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 09e47225-07a6-48db-9c59-e42421f41fe9 · outbound

This paper cites Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models.

PRM-Free Security Alignment of Large Models via Red Teaming and Adversarial Training Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models

Reference 72

Resolution: unresolved; no resolver link, observed 2026-08-06T17:35:48.445431Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0580d262-b859-4833-9516-6a4889a99700 · outbound

This paper cites an unresolved cited work.

PRM-Free Security Alignment of Large Models via Red Teaming and Adversarial Training Unresolved cited work

Reference 73

Resolution: unresolved; no resolver link, observed 2026-08-06T17:35:48.454219Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4360779b-94b6-4e1e-9494-feb52167a0a3 · outbound

This paper cites an unresolved cited work.

PRM-Free Security Alignment of Large Models via Red Teaming and Adversarial Training Unresolved cited work

Reference 74

Resolution: unresolved; raw_fallback, observed 2026-08-06T17:35:50.710417Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 5123c869-efcf-4be5-b141-c88b49df9fec · outbound

This paper cites Ensemble Adversarial Training: Attacks and Defenses.

PRM-Free Security Alignment of Large Models via Red Teaming and Adversarial Training Ensemble Adversarial Training: Attacks and Defenses

Reference 75

Resolution: unresolved; no resolver link, observed 2026-08-06T17:35:48.467325Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f7629bdb-6602-453e-9138-b15b6227f1d3 · outbound

This paper cites Robustness May Be at Odds with Accuracy.

PRM-Free Security Alignment of Large Models via Red Teaming and Adversarial Training Robustness May Be at Odds with Accuracy

Reference 76

Resolution: unresolved; no resolver link, observed 2026-08-06T17:35:48.474839Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aefb1499-3f67-469c-b28d-49a7afe5f42f · outbound

This paper cites Solving math word problems with process- and outcome-based feedback.

PRM-Free Security Alignment of Large Models via Red Teaming and Adversarial Training Solving math word problems with process- and outcome-based feedback

Reference 77

Resolution: unresolved; no resolver link, observed 2026-08-06T17:35:48.481517Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 923ae7d5-0634-43e6-9a9a-5af5f2a7d9bd · outbound

This paper cites Universal Adversarial Triggers for Attacking and Analyzing NLP.

PRM-Free Security Alignment of Large Models via Red Teaming and Adversarial Training Universal Adversarial Triggers for Attacking and Analyzing NLP

Reference 78

Resolution: unresolved; no resolver link, observed 2026-08-06T17:35:48.488605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1581c38e-115f-4014-b61b-b00e5933eef6 · outbound

This paper cites Adversarial GLUE: A Multi-Task Benchmark for Robustness Evaluation of Language Models.

PRM-Free Security Alignment of Large Models via Red Teaming and Adversarial Training Adversarial GLUE: A Multi-Task Benchmark for Robustness Evaluation of Language Models

Reference 79

Resolution: unresolved; no resolver link, observed 2026-08-06T17:35:48.496124Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c204d952-f567-4cbe-8f4a-21ee9e541aa8 · outbound

This paper cites an unresolved cited work.

PRM-Free Security Alignment of Large Models via Red Teaming and Adversarial Training Unresolved cited work

Reference 80

Resolution: unresolved; raw_fallback, observed 2026-08-06T17:35:50.688433Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 6314ad03-312d-443c-ada9-6fc5fa4f6b2f · outbound

This paper cites Natural Language Adversarial Defense through Synonym Encoding.

PRM-Free Security Alignment of Large Models via Red Teaming and Adversarial Training Natural Language Adversarial Defense through Synonym Encoding

Reference 81

Resolution: unresolved; no resolver link, observed 2026-08-06T17:35:48.513887Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0db3733e-7e4a-4a0e-ad85-2382dfd528e3 · outbound

This paper cites Self-Consistency Improves Chain of Thought Reasoning in Language Models.

PRM-Free Security Alignment of Large Models via Red Teaming and Adversarial Training Self-Consistency Improves Chain of Thought Reasoning in Language Models

Reference 82

Resolution: unresolved; no resolver link, observed 2026-08-06T17:35:48.522431Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 51d9b036-4365-4a9c-b6c8-01475b3ad402 · outbound

This paper cites an unresolved cited work.

PRM-Free Security Alignment of Large Models via Red Teaming and Adversarial Training Unresolved cited work

Reference 83

Resolution: unresolved; raw_fallback, observed 2026-08-06T17:35:50.666517Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 85d265f5-a6dd-4f4c-bada-8c01f9655ca4 · outbound

This paper cites Jailbroken: How Does LLM Safety Training Fail?.

PRM-Free Security Alignment of Large Models via Red Teaming and Adversarial Training Jailbroken: How Does LLM Safety Training Fail?

Reference 84

Resolution: unresolved; no resolver link, observed 2026-08-06T17:35:48.545520Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 822f62ee-5f4a-449b-8f91-4f6dc81ff76e · outbound

This paper cites Ethical and social risks of harm from Language Models.

PRM-Free Security Alignment of Large Models via Red Teaming and Adversarial Training Ethical and social risks of harm from Language Models

Reference 85

Resolution: unresolved; no resolver link, observed 2026-08-06T17:35:48.553979Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c54eaadb-dc35-4b7f-a38a-b6c517553455 · outbound

This paper cites Exploring The Landscape of Distributional Robustness for Question Answering Models.

PRM-Free Security Alignment of Large Models via Red Teaming and Adversarial Training Exploring The Landscape of Distributional Robustness for Question Answering Models

Reference 86

Resolution: unresolved; no resolver link, observed 2026-08-06T17:35:48.560955Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a8d55785-7081-4caa-a72b-e802dcad7c97 · outbound

This paper cites an unresolved cited work.

PRM-Free Security Alignment of Large Models via Red Teaming and Adversarial Training Unresolved cited work

Reference 87

Resolution: unresolved; raw_fallback, observed 2026-08-06T17:35:50.642464Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 72c27dd0-14f0-497b-baa6-8cddeb7a5a7a · outbound

This paper cites ReAct: Synergizing Reasoning and Acting in Language Models.

PRM-Free Security Alignment of Large Models via Red Teaming and Adversarial Training ReAct: Synergizing Reasoning and Acting in Language Models

Reference 88

Resolution: unresolved; no resolver link, observed 2026-08-06T17:35:48.576790Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 015af25f-f1e0-4a56-bfe7-fea6ed1beb49 · outbound

This paper cites Low-Resource Languages Jailbreak GPT-4.

PRM-Free Security Alignment of Large Models via Red Teaming and Adversarial Training Low-Resource Languages Jailbreak GPT-4

Reference 89

Resolution: unresolved; no resolver link, observed 2026-08-06T17:35:48.582594Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 84165dfd-1663-421f-965b-d33159b6d948 · outbound

This paper cites GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts.

PRM-Free Security Alignment of Large Models via Red Teaming and Adversarial Training GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts

Reference 90

Resolution: unresolved; no resolver link, observed 2026-08-06T17:35:48.591046Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 88de92c1-1199-4988-946c-6ef565782d31 · outbound

This paper cites an unresolved cited work.

PRM-Free Security Alignment of Large Models via Red Teaming and Adversarial Training Unresolved cited work

Reference 91

Resolution: unresolved; raw_fallback, observed 2026-08-06T17:35:50.613453Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 8b547ac2-a353-4344-a0a0-525fd1af06e9 · outbound

This paper cites Adversarial Training for Large Neural Language Models.

PRM-Free Security Alignment of Large Models via Red Teaming and Adversarial Training Adversarial Training for Large Neural Language Models

Reference 92

Resolution: unresolved; no resolver link, observed 2026-08-06T17:35:48.602842Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2e6d12c9-8c1c-48d0-a294-1eeebdd0ef52 · outbound

This paper cites FreeLB: Enhanced Adversarial Training for Natural Language Understanding.

PRM-Free Security Alignment of Large Models via Red Teaming and Adversarial Training FreeLB: Enhanced Adversarial Training for Natural Language Understanding

Reference 93

Resolution: unresolved; no resolver link, observed 2026-08-06T17:35:48.609506Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 350a898d-d298-48a8-bd4c-d7a3a13c8b39 · outbound

This paper cites Adversarial Training for High-Stakes Reliability.

PRM-Free Security Alignment of Large Models via Red Teaming and Adversarial Training Adversarial Training for High-Stakes Reliability

Reference 94

Resolution: unresolved; no resolver link, observed 2026-08-06T17:35:48.617525Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bba77999-6c87-41b9-bf16-cc2d7c3a81ad · outbound

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

PRM-Free Security Alignment of Large Models via Red Teaming and Adversarial Training Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 95

Resolution: unresolved; no resolver link, observed 2026-08-06T17:35:48.626472Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers