LLMs know their vulnerabilities: Uncover Safety Gaps through Natural Distribution Shifts

Some elements of a sociology of translation: domestication of the scallops and the fishermen of st brieuc bay

Michel Callon. 1984 · 1984

Earlier work this paper cites.

Evaluating the evaluation of diversity in natural language generation

Original

Guy Tevet and Jonathan Berant. 2020 · 2004

Earlier work this paper cites.

Measuring massive multitask language understanding

Original

Dan Hendrycks, Collin Burns, Steven Basart, Andy Zou, Mantas Mazeika, Dawn Song, and Jacob Steinhardt. 2020 · 2009

Earlier work this paper cites.

Minilmv2: Multi-head self-attention relation distillation for compressing pretrained transformers

Original

Wenhui Wang, Hangbo Bao, Shaohan Huang, Li Dong, and Furu Wei. 2020 · 2012

Earlier work this paper cites.

Pytorch: An imperative style, high-performance deep learning library

Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, et al. 2019 · 2019

Earlier work this paper cites.

Evaluating large language models trained on code

Original

Mark Chen, Jerry Tworek, Heewoo Jun, Qiming Yuan, Henrique Ponde De Oliveira Pinto, Jared Kaplan, Harri Edwards, Yuri Burda, Nicholas Joseph, Greg Brockman, et al. 2021 · 2021

Earlier work this paper cites.

Training verifiers to solve math word problems

Original

Karl Cobbe, Vineet Kosaraju, Mohammad Bavarian, Jacob Hilton, Reiichiro Nakano, Christopher Hesse, and John Schulman. 2021 · 2021

Earlier work this paper cites.

Lora: Low-rank adaptation of large language models

Edward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2021 · 2021

Earlier work this paper cites.

Training a helpful and harmless assistant with reinforcement learning from human feedback

Original

Yuntao Bai, Andy Jones, Kamal Ndousse, Amanda Askell, Anna Chen, Nova DasSarma, Dawn Drain, Stanislav Fort, Deep Ganguli, Tom Henighan, et al. 2022 · 2022

Earlier work this paper cites.

A holistic approach to undesired content detection

Original

Todor Markov, Chong Zhang, Sandhini Agarwal, Tyna Eloundou, Teddy Lee, Steven Adler, Angela Jiang, and Lilian Weng. 2022 · 2022

Earlier work this paper cites.

Training language models to follow instructions with human feedback

Long Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida, Carroll Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, et al. 2022 · 2022

Earlier work this paper cites.

Red teaming language models with language models

Original

Ethan Perez, Saffron Huang, Francis Song, Trevor Cai, Roman Ring, John Aslanides, Amelia Glaese, Nat McAleese, and Geoffrey Irving. 2022 · 2022

Earlier work this paper cites.

Bloom: A 176b-parameter open-access multilingual language model

Original

BigScience Workshop, Teven Le Scao, Angela Fan, Christopher Akiki, Ellie Pavlick, Suzana Ilić, Daniel Hesslow, Roman Castagné, Alexandra Sasha Luccioni, François Yvon, et al. 2022 · 2022

Earlier work this paper cites.

Detecting language model attacks with perplexity

Original

Gabriel Alon and Michael Kamfonas. 2023 · 2023

Earlier work this paper cites.

Defending against alignment-breaking attacks via robustly aligned llm

Original

Bochuan Cao, Yuanpu Cao, Lu Lin, and Jinghui Chen. 2023 · 2023

Earlier work this paper cites.

Explore, establish, exploit: Red teaming language models from scratch

Original

Stephen Casper, Jason Lin, Joe Kwon, Gatlen Culp, and Dylan Hadfield-Menell. 2023 · 2023

Earlier work this paper cites.

Jailbreaking black box large language models in twenty queries

Original

Patrick Chao, Alexander Robey, Edgar Dobriban, Hamed Hassani, George J Pappas, and Eric Wong. 2023 · 2023

Earlier work this paper cites.

Opencompass: A universal evaluation platform for foundation models

OpenCompass Contributors. 2023 · 2023

Earlier work this paper cites.

Multilingual jailbreak challenges in large language models

Original

Yue Deng, Wenxuan Zhang, Sinno Jialin Pan, and Lidong Bing. 2023 · 2023

Earlier work this paper cites.

Llama guard: Llm-based input-output safeguard for human-ai conversations

Original

Hakan Inan, Kartikeya Upasani, Jianfeng Chi, Rashi Rungta, Krithika Iyer, Yuning Mao, Michael Tontchev, Qing Hu, Brian Fuller, Davide Testuggine, et al. 2023 · 2023

Earlier work this paper cites.

Baseline defenses for adversarial attacks against aligned language models

Original

Neel Jain, Avi Schwarzschild, Yuxin Wen, Gowthami Somepalli, John Kirchenbauer, Ping-yeh Chiang, Micah Goldblum, Aniruddha Saha, Jonas Geiping, and Tom Goldstein. 2023 · 2023

Earlier work this paper cites.

Efficient memory management for large language model serving with pagedattention

Woosuk Kwon, Zhuohan Li, Siyuan Zhuang, Ying Sheng, Lianmin Zheng, Cody Hao Yu, Joseph E. Gonzalez, Hao Zhang, and Ion Stoica. 2023 · 2023

Earlier work this paper cites.

Measuring faithfulness in chain-of-thought reasoning

Original

Tamera Lanham, Anna Chen, Ansh Radhakrishnan, Benoit Steiner, Carson Denison, Danny Hernandez, Dustin Li, Esin Durmus, Evan Hubinger, Jackson Kernion, et al. 2023 · 2023

Earlier work this paper cites.

Autodan: Generating stealthy jailbreak prompts on aligned large language models

Original

Xiaogeng Liu, Nan Xu, Muhao Chen, and Chaowei Xiao. 2023 · 2023

Earlier work this paper cites.

Faithful chain-of-thought reasoning

Original

Qing Lyu, Shreya Havaldar, Adam Stein, Li Zhang, Delip Rao, Eric Wong, Marianna Apidianaki, and Chris Callison-Burch. 2023 · 2023

Cited alongside, same era.

Tree of attacks: Jailbreaking black-box llms automatically

Original

Anay Mehrotra, Manolis Zampetakis, Paul Kassianik, Blaine Nelson, Hyrum Anderson, Yaron Singer, and Amin Karbasi. 2023 · 2023

Cited alongside, same era.

Seallms–large language models for southeast asia

Original

Xuan-Phi Nguyen, Wenxuan Zhang, Xin Li, Mahani Aljunied, Qingyu Tan, Liying Cheng, Guanzheng Chen, Yue Deng, Sen Yang, Chaoqun Liu, et al. 2023 · 2023

Cited alongside, same era.

Gpt-3.5 turbo

OpenAI. 2023 · 2023

Cited alongside, same era.

Llm self defense: By self examination, llms know they are being tricked

Original

Beavertails: Towards improved safety alignment of llm via a human-preference dataset

Jiaming Ji, Mickel Liu, Josef Dai, Xuehai Pan, Chi Zhang, Ce Bian, Boyuan Chen, Ruiyang Sun, Yizhou Wang, and Yaodong Yang. 2024 · 2024

Closest in time.

Red queen: Safeguarding large language models against concealed multi-turn jailbreaking

Original

Yifan Jiang, Kriti Aggarwal, Tanmay Laud, Kashif Munir, Jay Pujara, and Subhabrata Mukherjee. 2024 · 2024

Closest in time.

Learning diverse attacks on large language models for robust red-teaming and safety tuning

Original

Seanie Lee, Minsu Kim, Lynn Cherif, David Dobre, Juho Lee, Sung Ju Hwang, Kenji Kawaguchi, Gauthier Gidel, Yoshua Bengio, Nikolay Malkin, et al. 2024 · 2024

Closest in time.

Sofa: Shielded on-the-fly alignment via priority rule following

Original

Xinyu Lu, Bowen Yu, Yaojie Lu, Hongyu Lin, Haiyang Yu, Le Sun, Xianpei Han, and Yongbin Li. 2024 · 2024

Closest in time.