RedRFT: A Light-Weight Benchmark for Reinforcement Fine-Tuning-Based Red Teaming | Paper Citation Record

Observation f175e702-865c-41fb-9b1a-e41681f97f73 · outbound

This paper cites Training language models to follow instructions with human feedback.

RedRFT: A Light-Weight Benchmark for Reinforcement Fine-Tuning-Based Red Teaming Training language models to follow instructions with human feedback

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:55:21.772227Z

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 dc690450-026d-45d9-979c-2b506f6cd357 · outbound

This paper cites Unsolved Problems in ML Safety.

RedRFT: A Light-Weight Benchmark for Reinforcement Fine-Tuning-Based Red Teaming Unsolved Problems in ML Safety

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T10:55:19.968574Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 17cc6a00-b7c4-4ae6-8e15-cffb15d9a430 · outbound

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

RedRFT: A Light-Weight Benchmark for Reinforcement Fine-Tuning-Based Red Teaming Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T10:55:19.978526Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7a20bf65-7fe3-483d-939c-4c47a640d3ac · outbound

This paper cites Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks.

RedRFT: A Light-Weight Benchmark for Reinforcement Fine-Tuning-Based Red Teaming Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T10:55:19.989451Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 381be7f1-ef81-4ae9-b907-d175e55a1aa0 · outbound

This paper cites AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models.

RedRFT: A Light-Weight Benchmark for Reinforcement Fine-Tuning-Based Red Teaming AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T10:55:20.000342Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0c503a99-6875-4ae6-9011-00c5c4b72415 · outbound

This paper cites Query-Efficient Black-Box Red Teaming via Bayesian Optimization.

RedRFT: A Light-Weight Benchmark for Reinforcement Fine-Tuning-Based Red Teaming Query-Efficient Black-Box Red Teaming via Bayesian Optimization

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T10:55:20.011756Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 853fdc58-f2a8-47a3-aa54-12b83aee6b31 · outbound

This paper cites Large Language Models as Optimizers.

RedRFT: A Light-Weight Benchmark for Reinforcement Fine-Tuning-Based Red Teaming Large Language Models as Optimizers

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T10:55:20.027907Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cac5389b-1754-4149-881a-773667e75f80 · outbound

This paper cites Red Teaming Language Models with Language Models.

RedRFT: A Light-Weight Benchmark for Reinforcement Fine-Tuning-Based Red Teaming Red Teaming Language Models with Language Models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T10:55:20.037233Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 382dc7af-da47-42fe-b859-be941488cdc2 · outbound

This paper cites Discovering language model behaviors with model-written evaluations.

RedRFT: A Light-Weight Benchmark for Reinforcement Fine-Tuning-Based Red Teaming Discovering language model behaviors with model-written evaluations

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:55:21.752229Z

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 b06c2a86-7fd2-4537-92e4-511cf268330d · outbound

This paper cites Attack Prompt Generation for Red Teaming and Defending Large Language Models.

RedRFT: A Light-Weight Benchmark for Reinforcement Fine-Tuning-Based Red Teaming Attack Prompt Generation for Red Teaming and Defending Large Language Models

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T10:55:20.050296Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ae34b8d3-fbac-43ec-a207-7dba2ef5b36d · outbound

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

RedRFT: A Light-Weight Benchmark for Reinforcement Fine-Tuning-Based Red Teaming Explore, Establish, Exploit: Red Teaming Language Models from Scratch

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T10:55:20.057855Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e93d054-5718-4965-a335-c1904c8f7421 · outbound

This paper cites Curiosity-driven Red-teaming for Large Language Models.

RedRFT: A Light-Weight Benchmark for Reinforcement Fine-Tuning-Based Red Teaming Curiosity-driven Red-teaming for Large Language Models

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T10:55:20.071156Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 87957fe8-5de1-449b-9104-f13c3a4e5268 · outbound

This paper cites DiveR-CT: Diversity-enhanced Red Teaming Large Language Model Assistants with Relaxing Constraints.

RedRFT: A Light-Weight Benchmark for Reinforcement Fine-Tuning-Based Red Teaming DiveR-CT: Diversity-enhanced Red Teaming Large Language Model Assistants with Relaxing Constraints

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:55:21.732369Z

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 38a38d83-3fff-443d-a6f5-8bef94cf5d1d · outbound

This paper cites CALM: Curiosity-Driven Auditing for Large Language Models.

RedRFT: A Light-Weight Benchmark for Reinforcement Fine-Tuning-Based Red Teaming CALM: Curiosity-Driven Auditing for Large Language Models

Reference 14

Resolution: verified exact; local_arxiv, observed 2026-08-07T10:55:20.946358Z

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 9b2881ed-b30b-4c61-9fb6-045bdf8030f9 · outbound

This paper cites CIM: Constrained Intrinsic Motivation for Reinforcement Learning.

RedRFT: A Light-Weight Benchmark for Reinforcement Fine-Tuning-Based Red Teaming CIM: Constrained Intrinsic Motivation for Reinforcement Learning

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:55:21.716179Z

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 a9f03fec-4556-4d63-a544-00dd68645c7e · outbound

This paper cites Proximal Policy Optimization Algorithms.

RedRFT: A Light-Weight Benchmark for Reinforcement Fine-Tuning-Based Red Teaming Proximal Policy Optimization Algorithms

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T10:55:20.103060Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d7c316e8-2e99-4ee5-8f7d-4ed2de119e3a · outbound

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

RedRFT: A Light-Weight Benchmark for Reinforcement Fine-Tuning-Based Red Teaming Jailbreaking Black Box Large Language Models in Twenty Queries

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T10:55:20.110906Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 33da88f3-d4b9-4424-ba63-b3cec21e6766 · outbound

This paper cites Tree of attacks: Jailbreaking black-box llms automatically.

RedRFT: A Light-Weight Benchmark for Reinforcement Fine-Tuning-Based Red Teaming Tree of attacks: Jailbreaking black-box llms automatically

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:55:21.699718Z

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 9a313817-9950-4f83-a6e9-e015f0e9b66c · outbound

This paper cites How johnny can persuade llms to jailbreak them: Rethinking persuasion to challenge ai safety by humanizing llms.

RedRFT: A Light-Weight Benchmark for Reinforcement Fine-Tuning-Based Red Teaming How johnny can persuade llms to jailbreak them: Rethinking persuasion to challenge ai safety by humanizing llms

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:55:21.683610Z

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 ad3fbefa-428f-42c0-8b06-d0a1cd315538 · outbound

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

RedRFT: A Light-Weight Benchmark for Reinforcement Fine-Tuning-Based Red Teaming GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T10:55:20.132349Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8ea00912-2743-44fc-9d6c-47e46ac6d4a0 · outbound

This paper cites https://github.com/ huggingface/trl.

RedRFT: A Light-Weight Benchmark for Reinforcement Fine-Tuning-Based Red Teaming https://github.com/ huggingface/trl

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:55:21.667522Z

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 381dc6ef-ac5c-49ae-b65b-9b98b331c786 · outbound

This paper cites Direct preference optimization: Your language model is secretly a reward model.

RedRFT: A Light-Weight Benchmark for Reinforcement Fine-Tuning-Based Red Teaming Direct preference optimization: Your language model is secretly a reward model

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:55:21.650520Z

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 908c75a0-f94a-4865-a9f4-8d9bbe7e8e9f · outbound

This paper cites OpenRLHF: An Easy-to-use, Scalable and High-performance RLHF Framework.

RedRFT: A Light-Weight Benchmark for Reinforcement Fine-Tuning-Based Red Teaming OpenRLHF: An Easy-to-use, Scalable and High-performance RLHF Framework

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T10:55:20.161901Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 08285b22-1570-4643-add2-818f40fc8436 · outbound

This paper cites DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models.

RedRFT: A Light-Weight Benchmark for Reinforcement Fine-Tuning-Based Red Teaming DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T10:55:20.167213Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4ed6cbbe-99a6-41cd-ae6a-9d427b1592b3 · outbound

This paper cites Is Reinforcement Learning (Not) for Natural Language Processing: Benchmarks, Baselines, and Building Blocks for Natural Language Policy Optimization.

RedRFT: A Light-Weight Benchmark for Reinforcement Fine-Tuning-Based Red Teaming Is Reinforcement Learning (Not) for Natural Language Processing: Benchmarks, Baselines, and Building Blocks for Natural Language Policy Optimization

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T10:55:20.175303Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 87e49c1d-7f06-4080-852f-d4786f7fc0d8 · outbound

This paper cites GPT-4o System Card.

RedRFT: A Light-Weight Benchmark for Reinforcement Fine-Tuning-Based Red Teaming GPT-4o System Card

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T10:55:20.188583Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8aeef9cb-e71d-4f57-998c-6696040a3799 · outbound

This paper cites DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning.

RedRFT: A Light-Weight Benchmark for Reinforcement Fine-Tuning-Based Red Teaming DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T10:55:20.197684Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b4b230da-84bc-4768-b4c3-268d49f2c8c0 · outbound

This paper cites What Matters In On-Policy Reinforcement Learning? A Large-Scale Empirical Study.

RedRFT: A Light-Weight Benchmark for Reinforcement Fine-Tuning-Based Red Teaming What Matters In On-Policy Reinforcement Learning? A Large-Scale Empirical Study

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T10:55:20.205546Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0ab1fa87-310f-4571-ad83-a3e2d187c08c · outbound

This paper cites URLB: Unsupervised Reinforcement Learning Benchmark.

RedRFT: A Light-Weight Benchmark for Reinforcement Fine-Tuning-Based Red Teaming URLB: Unsupervised Reinforcement Learning Benchmark

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T10:55:20.212381Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 40351ced-22cb-4d3f-a5c6-0c5bc8cea678 · outbound

This paper cites Exploration by Random Network Distillation.

RedRFT: A Light-Weight Benchmark for Reinforcement Fine-Tuning-Based Red Teaming Exploration by Random Network Distillation

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-07T10:55:20.217369Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a180c0b8-31ba-47a6-8997-c72253260825 · outbound

This paper cites Large-Scale Study of Curiosity-Driven Learning.

RedRFT: A Light-Weight Benchmark for Reinforcement Fine-Tuning-Based Red Teaming Large-Scale Study of Curiosity-Driven Learning

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-07T10:55:20.225697Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2a95946f-6344-4dda-9356-a73851590d2b · outbound

This paper cites Made: Exploration via maximizing deviation from explored regions.

RedRFT: A Light-Weight Benchmark for Reinforcement Fine-Tuning-Based Red Teaming Made: Exploration via maximizing deviation from explored regions

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:55:21.632220Z

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 87a2b6a5-e034-47bd-b063-0a4a9d478ccf · outbound

This paper cites Aps: Active pretraining with successor features.

RedRFT: A Light-Weight Benchmark for Reinforcement Fine-Tuning-Based Red Teaming Aps: Active pretraining with successor features

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:55:21.615141Z

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 9902af5a-2f2c-4bf3-9db7-8616ceb4b872 · outbound

This paper cites Provably efficient maximum entropy exploration.

RedRFT: A Light-Weight Benchmark for Reinforcement Fine-Tuning-Based Red Teaming Provably efficient maximum entropy exploration

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:55:21.597103Z

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 46edf65b-7e79-4371-8a30-383151690748 · outbound

This paper cites Task-agnostic exploration via policy gradient of a non-parametric state entropy estimate.

RedRFT: A Light-Weight Benchmark for Reinforcement Fine-Tuning-Based Red Teaming Task-agnostic exploration via policy gradient of a non-parametric state entropy estimate

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:55:21.579769Z

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 63dc068b-a992-475e-836b-fa81c7bae7ed · outbound

This paper cites Behavior from the void: Unsupervised active pre-training.

RedRFT: A Light-Weight Benchmark for Reinforcement Fine-Tuning-Based Red Teaming Behavior from the void: Unsupervised active pre-training

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:55:21.563908Z

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 9623f91d-a38e-4822-b268-deb1e410a141 · outbound

This paper cites METRA: Scalable Unsupervised RL with Metric-Aware Abstraction.

RedRFT: A Light-Weight Benchmark for Reinforcement Fine-Tuning-Based Red Teaming METRA: Scalable Unsupervised RL with Metric-Aware Abstraction

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-07T10:55:20.265825Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5debbec7-ef51-442b-821b-4bede4fed053 · outbound

This paper cites Variational Intrinsic Control.

RedRFT: A Light-Weight Benchmark for Reinforcement Fine-Tuning-Based Red Teaming Variational Intrinsic Control

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-07T10:55:20.272855Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e03d3241-ec77-42e9-b744-9191bd314146 · outbound

This paper cites Dynamics-Aware Unsupervised Discovery of Skills.

RedRFT: A Light-Weight Benchmark for Reinforcement Fine-Tuning-Based Red Teaming Dynamics-Aware Unsupervised Discovery of Skills

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-07T10:55:20.279140Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3b9a831c-c371-4a1a-8e9f-7b704e083dd4 · outbound

This paper cites CIC: Contrastive Intrinsic Control for Unsupervised Skill Discovery.

RedRFT: A Light-Weight Benchmark for Reinforcement Fine-Tuning-Based Red Teaming CIC: Contrastive Intrinsic Control for Unsupervised Skill Discovery

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-07T10:55:20.286572Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7edfc9e9-e9a3-4498-861d-cc2b94dbd0e2 · outbound

This paper cites Lipschitz-constrained unsupervised skill discovery.

RedRFT: A Light-Weight Benchmark for Reinforcement Fine-Tuning-Based Red Teaming Lipschitz-constrained unsupervised skill discovery

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:55:21.546382Z

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 400927c6-059a-448b-99bc-51f51c43c6dc · outbound

This paper cites Contrastive learning as goal-conditioned reinforcement learning.

RedRFT: A Light-Weight Benchmark for Reinforcement Fine-Tuning-Based Red Teaming Contrastive learning as goal-conditioned reinforcement learning

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:55:21.529985Z

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 663a31b7-a700-41ba-ad81-9d45e84ce291 · outbound

This paper cites Behavior contrastive learning for unsupervised skill discovery.

RedRFT: A Light-Weight Benchmark for Reinforcement Fine-Tuning-Based Red Teaming Behavior contrastive learning for unsupervised skill discovery

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:55:21.514043Z

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 58364df4-b6e3-41b3-b97f-1b27c1a821fb · outbound

This paper cites Constrained Intrinsic Motivation for Reinforcement Learning.

RedRFT: A Light-Weight Benchmark for Reinforcement Fine-Tuning-Based Red Teaming Constrained Intrinsic Motivation for Reinforcement Learning

Reference 44

Resolution: verified exact; local_arxiv, observed 2026-08-07T10:55:20.543202Z

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 6827f958-515b-4993-9e21-ce34312fc62d · outbound

This paper cites Texygen: A benchmarking platform for text generation models.

RedRFT: A Light-Weight Benchmark for Reinforcement Fine-Tuning-Based Red Teaming Texygen: A benchmarking platform for text generation models

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:55:21.495004Z

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 54a87242-300d-4a7e-ac4e-925cfcd01723 · outbound

This paper cites Guidelines: • The answer NA means that the abstract and introduction do not include the claims made in the paper.

RedRFT: A Light-Weight Benchmark for Reinforcement Fine-Tuning-Based Red Teaming Guidelines: • The answer NA means that the abstract and introduction do not include the claims made in the paper

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:55:21.471942Z

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 3b7f25ba-2680-4287-a94a-9c13dfc3475a · outbound

This paper cites Limitations.

RedRFT: A Light-Weight Benchmark for Reinforcement Fine-Tuning-Based Red Teaming Limitations

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:55:21.445445Z

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 43689bd1-c7ff-4d64-983c-b29be3ea708a · outbound

This paper cites Thus, we do not provide original theoretical results of the each baseline method.

RedRFT: A Light-Weight Benchmark for Reinforcement Fine-Tuning-Based Red Teaming Thus, we do not provide original theoretical results of the each baseline method

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:55:21.421981Z

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 2e769d34-be7d-4293-9717-f63132a532ba · outbound

This paper cites Our experiment results can be easily reproduced with a simple environment setup, the default config files, and the prepared shell scripts.

RedRFT: A Light-Weight Benchmark for Reinforcement Fine-Tuning-Based Red Teaming Our experiment results can be easily reproduced with a simple environment setup, the default config files, and the prepared shell scripts

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:55:21.401126Z

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 729bd66c-a64a-44e7-8592-905e34f9ad0e · outbound

This paper cites Guidelines: • The answer NA means that paper does not include experiments requiring code.

RedRFT: A Light-Weight Benchmark for Reinforcement Fine-Tuning-Based Red Teaming Guidelines: • The answer NA means that paper does not include experiments requiring code

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:55:21.375072Z

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 541639fb-fc2c-4f21-b843-2c2018df7c94 · outbound

This paper cites Guidelines: • The answer NA means that the paper does not include experiments.

RedRFT: A Light-Weight Benchmark for Reinforcement Fine-Tuning-Based Red Teaming Guidelines: • The answer NA means that the paper does not include experiments

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:55:21.353669Z

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 b11c78d3-4c70-461a-bdad-6b0d36c732ab · outbound

This paper cites Guidelines: • The answer NA means that the paper does not include experiments.

RedRFT: A Light-Weight Benchmark for Reinforcement Fine-Tuning-Based Red Teaming Guidelines: • The answer NA means that the paper does not include experiments

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:55:21.331413Z

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 ac8777d8-1fcb-4c87-9979-fd85f64a6bfc · outbound

This paper cites Guidelines: • The answer NA means that the paper does not include experiments.

RedRFT: A Light-Weight Benchmark for Reinforcement Fine-Tuning-Based Red Teaming Guidelines: • The answer NA means that the paper does not include experiments

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:55:21.308529Z

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 5f88aa89-5bf3-4ead-bab4-b454b1aa1367 · outbound

This paper cites Guidelines: • The answer NA means that the authors have not reviewed the NeurIPS Code of Ethics.

RedRFT: A Light-Weight Benchmark for Reinforcement Fine-Tuning-Based Red Teaming Guidelines: • The answer NA means that the authors have not reviewed the NeurIPS Code of Ethics

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:55:21.289513Z

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 bc5483a2-b170-4143-a810-6eb120b8953f · outbound

This paper cites Guidelines: • The answer NA means that there is no societal impact of the work performed.

RedRFT: A Light-Weight Benchmark for Reinforcement Fine-Tuning-Based Red Teaming Guidelines: • The answer NA means that there is no societal impact of the work performed

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:55:21.269397Z

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 87174eda-9204-4f40-ad21-68fde8abdc1c · outbound

This paper cites Guidelines: • The answer NA means that the paper poses no such risks.

RedRFT: A Light-Weight Benchmark for Reinforcement Fine-Tuning-Based Red Teaming Guidelines: • The answer NA means that the paper poses no such risks

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:55:21.251148Z

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 bdc3f549-f526-4d11-8653-dc3203cafff8 · outbound

This paper cites Guidelines: • The answer NA means that the paper does not use existing assets.

RedRFT: A Light-Weight Benchmark for Reinforcement Fine-Tuning-Based Red Teaming Guidelines: • The answer NA means that the paper does not use existing assets

Reference 57

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:55:21.234174Z

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 3a24e7df-fd5c-44df-ba83-91600cc58698 · outbound

This paper cites Please refer to https: //github.com/x-zheng16/RedRFT.git for the document.

RedRFT: A Light-Weight Benchmark for Reinforcement Fine-Tuning-Based Red Teaming Please refer to https: //github.com/x-zheng16/RedRFT.git for the document

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:55:21.217962Z

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 d7fb2682-a2e7-4ba4-af7f-21bf833ea638 · outbound

This paper cites Guidelines: • The answer NA means that the paper does not involve crowdsourcing nor research with human subjects.

RedRFT: A Light-Weight Benchmark for Reinforcement Fine-Tuning-Based Red Teaming Guidelines: • The answer NA means that the paper does not involve crowdsourcing nor research with human subjects

Reference 59

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:55:21.200211Z

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 431ab6db-b213-4dd0-aa74-f9bc67e192cd · outbound

This paper cites Guidelines: 25 • The answer NA means that the paper does not involve crowdsourcing nor research with human subjects.

RedRFT: A Light-Weight Benchmark for Reinforcement Fine-Tuning-Based Red Teaming Guidelines: 25 • The answer NA means that the paper does not involve crowdsourcing nor research with human subjects

Reference 60

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:55:21.180137Z

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 8f459fa7-9125-4e1c-9e78-53da5a87cf8b · outbound

This paper cites an unresolved cited work.

RedRFT: A Light-Weight Benchmark for Reinforcement Fine-Tuning-Based Red Teaming Unresolved cited work

Reference 61

Resolution: unresolved; raw_fallback, observed 2026-08-07T10:55:21.162162Z

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.

Coverage vector

Reference resolution

Outbound references

Pith citing papers