Research graph
References from Evolving Diverse Red-Team Language Models in Multi-Round Multi-Agent Games. Local targets link to admitted publications; unresolved targets remain external evidence.
Introducing chatGPT
2022 · External reference
Meet claude
2023 · External reference
10.18653/v1/2020.findings-emnlp.301
10.18653/v1/2020.findings-emnlp.301 · External reference
10.1038/s42256-021-00359-2
10.1038/s42256-021-00359-2 · External reference
Extracting training data from large language models
External reference
10.1145/3442188.3445922
10.1145/3442188.3445922 · External reference
10.18653/v1/2021.naacl-main.235
10.18653/v1/2021.naacl-main.235 · External reference
Red teaming language models to reduce harms: Methods, scaling behaviors, and lessons learned
2022 · External reference
Recursively summarizing books with human feedback
2021 · External reference
10.18653/v1/d19-1461
10.18653/v1/d19-1461 · External reference
10.18653/v1/2022.emnlp-main.225
10.18653/v1/2022.emnlp-main.225 · External reference
GPTFUZZER: Red teaming large language models with auto-generated jailbreak prompts
2023 · External reference
10.1162/tacl_a_00639
10.1162/tacl_a_00639 · External reference
Universal and transferable adversarial attacks on aligned language models
2023 · External reference
10.18653/v1/2024.eacl-long.175
10.18653/v1/2024.eacl-long.175 · External reference
10.1609/aaai.v34i05.6400
10.1609/aaai.v34i05.6400 · External reference
Curiosity-driven red-teaming for large language models
2024 · External reference
Explore, establish, exploit: Red teaming language models from scratch
2023 · External reference
10.4337/9781781950777.00022
10.4337/9781781950777.00022 · External reference
Can LLMs generate random numbers? Evaluating LLM sampling in controlled domains
External reference
ODIN: Disentangled reward mitigates hacking in RLHF
2024 · External reference
10.1609/aaai.v36i10.21307
10.1609/aaai.v36i10.21307 · External reference
10.52202/068431-2011
10.52202/068431-2011 · External reference
Real world games look like spinning tops
External reference
A unified game-theoretic approach to multiagent reinforcement learning
External reference
10.1016/j.jet.2005.12.010
10.1016/j.jet.2005.12.010 · External reference
Learning to summarize with human feedback
External reference
10.1162/tacl_a_00639
10.1162/tacl_a_00639 · External reference
10.18653/v1/2020.acl-main.442
10.18653/v1/2020.acl-main.442 · External reference
10.18653/v1/2021.emnlp-main.696
10.18653/v1/2021.emnlp-main.696 · External reference
10.18653/v1/p19-1262
10.18653/v1/p19-1262 · External reference
10.1109/icassp.2019.8682430
10.1109/icassp.2019.8682430 · External reference
Constitutional AI: Harmlessness from AI feedback
2022 · External reference
10.52202/075280-0115
10.52202/075280-0115 · External reference
Neural text generation with unlikelihood training
2019 · External reference
Negative training for neural dialogue response generation
2019 · External reference
10.18653/v1/2020.acl-main.428
10.18653/v1/2020.acl-main.428 · External reference
Unresolved reference
2016 · External reference
Unresolved reference
2001 · External reference
Deep counterfactual regret minimization
External reference
Planning in the presence of cost functions controlled by an adversary
External reference
Proximal policy optimization algorithms
2017 · External reference
10.1017/cbo9780511811654
10.1017/cbo9780511811654 · External reference
Modelling behavioural diversity for learning in open-ended games
External reference
Towards unifying behavioral and response diversity for open-ended learning in zero-sum games
External reference
Effective diversity in population based reinforcement learning
External reference
10.52202/068431-0751
10.52202/068431-0751 · External reference
10.1016/j.geb.2005.08.005
10.1016/j.geb.2005.08.005 · External reference
Stanford alpaca: An instruction-following LLaMA model
2023 · External reference
10.52202/075280-1072
10.52202/075280-1072 · External reference
10.1080/01621459.1967.10482901
10.1080/01621459.1967.10482901 · External reference
10.1109/tpami.2026.3660147
10.1109/tpami.2026.3660147 · External reference
Understanding the effects of RLHF on LLM generalisation and diversity
External reference
Improving neural language modeling via adversarial training
External reference
Llama 2: Open foundation and fine-tuned chat models
2023 · External reference
10.1007/978-3-031-51630-6_6
10.1007/978-3-031-51630-6_6 · External reference
Visualizing data using t-SNE
2008 · External reference
