HarmLevelBench: Evaluating Harm-Level Compliance and the Impact of Quantization on Model Alignment

Su Lin Blodgett, Solon Barocas, Hal Daumé III, Hanna Wallach, Language (Technology) is Power: A Critical Survey of "Bias" in NLP , 2020. arXiv:2005.14050 [cs.CL]

Original

2005

Earlier work this paper cites.

Long Ouyang, Jeff Wu, Xu Jiang, Diogo Almeida, Carroll L. Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, John Schulman, Jacob Hilton, Fraser Kelton, Luke Miller, Maddie Simens, Amanda Askell, Peter Welinder, Paul Christiano, Jan Leike, Ryan Lowe, Training language models to follow instructions with human feedback , 2022. arXiv:2203.02155 [cs.CL]. https://arxiv.org/abs/2203.02155

Original

2022

Earlier work this paper cites.

Rohan Anil et al., PaLM 2 Technical Report , 2023. arXiv:2305.10403 [cs.CL]

Original

2023

Earlier work this paper cites.

Andy Zou, Zifan Wang, Nicholas Carlini, Milad Nasr, J. Zico Kolter, Matt Fredrikson, Universal and Transferable Adversarial Attacks on Aligned Language Models , 2023. arXiv:2307.15043 [cs.CL]. https://arxiv.org/abs/2307.15043

Original

2023

Earlier work this paper cites.

Maximilian Mozes, Xuanli He, Bennett Kleinberg, Lewis D. Griffin, Use of LLMs for Illicit Purposes: Threats, Prevention Measures, and Vulnerabilities , 2023. arXiv:2308.12833 [cs.CL]. https://arxiv.org/abs/2308.12833

Original

2023

Earlier work this paper cites.

Elias Frantar, Saleh Ashkboos, Torsten Hoefler, Dan Alistarh, GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers , 2023. arXiv:2210.17323 [cs.LG]. https://arxiv.org/abs/2210.17323

Original

2023

Earlier work this paper cites.

OpenAI, GPT-4 , 2023. https://platform.openai.com/docs/models/gpt-4 , Accessed: 2024-08-20

2024

Cited alongside, same era.

Rémi Munos, Michal Valko, Daniele Calandriello, Mohammad Gheshlaghi Azar, Mark Rowland, Zhaohan Daniel Guo, Yunhao Tang, Matthieu Geist, Thomas Mesnard, Andrea Michi, Marco Selvi, Sertan Girgin, Nikola Momchev, Olivier Bachem, Daniel J. Mankowitz, Doina Precup, Bilal Piot, Nash Learning from Human Feedback , 2024. arXiv:2312.00886 [stat.ML]. https://arxiv.org/abs/2312.00886

Original

2024

Cited alongside, same era.

Arijit Ghosh Chowdhury, Md Mofijul Islam, Vaibhav Kumar, Faysal Hossain Shezan, Vaibhav Kumar, Vinija Jain, Aman Chadha, Breaking Down the Defenses: A Comparative Survey of Attacks on Large Language Models , 2024. arXiv:2403.04786 [cs.CR]. https://arxiv.org/abs/2403.04786

Original

2024

Cited alongside, same era.

Patrick Chao, Alexander Robey, Edgar Dobriban, Hamed Hassani, George J. Pappas, Eric Wong, Jailbreaking Black Box Large Language Models in Twenty Queries , 2024. arXiv:2310.08419 [cs.LG]. https://arxiv.org/abs/2310.08419

Original

2024

Cited alongside, same era.

Divyanshu Kumar, Anurakt Kumar, Sahil Agarwal, Prashanth Harshangi, Fine-Tuning, Quantization, and LLMs: Navigating Unintended Outcomes , 2024. arXiv:2404.04392 [cs.CR]. https://arxiv.org/abs/2404.04392

Original

2024

Closest in time.

Paul Röttger, Hannah Rose Kirk, Bertie Vidgen, Giuseppe Attanasio, Federico Bianchi, Dirk Hovy, XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models , 2024. arXiv:2308.01263 [cs.CL]. https://arxiv.org/abs/2308.01263

Original

2024

Closest in time.

Zhexin Zhang, Leqi Lei, Lindong Wu, Rui Sun, Yongkang Huang, Chong Long, Xiao Liu, Xuanyu Lei, Jie Tang, Minlie Huang, SafetyBench: Evaluating the Safety of Large Language Models , 2024. arXiv:2309.07045 [cs.CL]. https://arxiv.org/abs/2309.07045

Original

2024

Closest in time.

Xiaogeng Liu, Nan Xu, Muhao Chen, Chaowei Xiao, AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models , 2024. arXiv:2310.04451 [cs.CL]. https://arxiv.org/abs/2310.04451

Original

2024

Closest in time.