An Embarrassingly Simple Defense Against LLM Abliteration Attacks

Exploring the limits of transfer learning with a unified text-to-text transformer

Original

Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J. Liu. 2023 · 1910

Earlier work this paper cites.

Language models are few-shot learners

Original

Tom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, Sandhini Agarwal, Ariel Herbert-Voss, Gretchen Krueger, Tom Henighan, Rewon Child, Aditya Ramesh, Daniel M. Ziegler, Jeffrey Wu, Clemens Winter, and 12 others. 2020 · 2005

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. 2021 · 2009

Earlier work this paper cites.

Bot-adversarial dialogue for safe conversational agents

Jing Xu, Da Ju, Margaret Li, Y-Lan Boureau, Jason Weston, and Emily Dinan. 2021 · 2021

Earlier work this paper cites.

Red teaming language models to reduce harms: Methods, scaling behaviors, and lessons learned

Original

Deep Ganguli, Liane Lovitt, Jackson Kernion, Amanda Askell, Yuntao Bai, Saurav Kadavath, Ben Mann, Ethan Perez, Nicholas Schiefer, Kamal Ndousse, Andy Jones, Sam Bowman, Anna Chen, Tom Conerly, Nova DasSarma, Dawn Drain, Nelson Elhage, Sheer El-Showk, Stanislav Fort, and 17 others. 2022 · 2022

Earlier work this paper cites.

Training language models to follow instructions with human feedback

Original

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, and Ryan Lowe. 2022 · 2022

Earlier work this paper cites.

Free dolly: Introducing the world’s first truly open instruction-tuned llm

Mike Conover, Matt Hayes, Ankit Mathur, Jianwei Xie, Jun Wan, Sam Shah, Ali Ghodsi, Patrick Wendell, Matei Zaharia, and Reynold Xin. 2023 · 2023

Earlier work this paper cites.

A confederacy of models: a comprehensive evaluation of llms on creative writing

Original

Carlos Gómez-Rodríguez and Paul Williams. 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, and Madian Khabsa. 2023 · 2023

Earlier work this paper cites.

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

Original

Jiaming Ji, Mickel Liu, Juntao Dai, Xuehai Pan, Chi Zhang, Ce Bian, Chi Zhang, Ruiyang Sun, Yizhou Wang, and Yaodong Yang. 2023 · 2023

Earlier work this paper cites.

Evaluating open-domain question answering in the era of large language models

Original

Ehsan Kamalloo, Nouha Dziri, Charles L. A. Clarke, and Davood Rafiei. 2023 · 2023

Earlier work this paper cites.

Training socially aligned language models on simulated social interactions

Original

Ruibo Liu, Ruixin Yang, Chenyan Jia, Ge Zhang, Denny Zhou, Andrew M. Dai, Diyi Yang, and Soroush Vosoughi. 2023 · 2023

Earlier work this paper cites.

Tdc 2023 (llm edition): The trojan detection challenge

Mantas Mazeika, Andy Zou, Norman Mu, Long Phan, Zifan Wang, Chunru Yu, Adam Khoja, Fengqing Jiang, Aidan O’Gara, Ellie Sakhaee, Zhen Xiang, Arezoo Rajabi, Dan Hendrycks, Radha Poovendran, Bo Li, and David Forsyth. 2023 · 2023

Earlier work this paper cites.

Instruction tuning with gpt-4

Original

Baolin Peng, Chunyuan Li, Pengcheng He, Michel Galley, and Jianfeng Gao. 2023 · 2023

Earlier work this paper cites.

Fine-tuning aligned language models compromises safety, even when users do not intend to!

Original

Xiangyu Qi, Yi Zeng, Tinghao Xie, Pin-Yu Chen, Ruoxi Jia, Prateek Mittal, and Peter Henderson. 2023 · 2023

Earlier work this paper cites.

Llama 2: Open foundation and fine-tuned chat models

Original

Hugo Touvron, Louis Martin, Kevin Stone, Peter Albert, Amjad Almahairi, Yasmine Babaei, Nikolay Bashlykov, Soumya Batra, Prajjwal Bhargava, Shruti Bhosale, Dan Bikel, Lukas Blecher, Cristian Canton Ferrer, Moya Chen, Guillem Cucurull, David Esiobu, Jude Fernandes, Jeremy Fu, Wenyin Fu, and 49 others. 2023 · 2023

Earlier work this paper cites.

Jailbroken: How does llm safety training fail?

Original

Alexander Wei, Nika Haghtalab, and Jacob Steinhardt. 2023 · 2023

Earlier work this paper cites.

Make them spill the beans! coercive knowledge extraction from (production) llms

Original

Zhuo Zhang, Guangyu Shen, Guanhong Tao, Siyuan Cheng, and Xiangyu Zhang. 2023 · 2023

Earlier work this paper cites.

Judging llm-as-a-judge with mt-bench and chatbot arena

Original

Lianmin Zheng, Wei-Lin Chiang, Ying Sheng, Siyuan Zhuang, Zhanghao Wu, Yonghao Zhuang, Zi Lin, Zhuohan Li, Dacheng Li, Eric P. Xing, Hao Zhang, Joseph E. Gonzalez, and Ion Stoica. 2023 · 2023

Earlier work this paper cites.

LIMA: Less Is More for Alignment

Chunting Zhou, Pengfei Liu, Puxin Xu, Srini Iyer, Jiao Sun, Yuning Mao, Xuezhe Ma, Avia Efrat, Ping Yu, Lili Yu, Susan Zhang, Gargi Ghosh, Mike Lewis, Luke Zettlemoyer, and Omer Levy. 2023 · 2023

Cited alongside, same era.

Universal and transferable adversarial attacks on aligned language models

Original

Andy Zou, Zifan Wang, Nicholas Carlini, Milad Nasr, J. Zico Kolter, and Matt Fredrikson. 2023 · 2023

Cited alongside, same era.

Refusal in Language Models Is Mediated by a Single Direction

Andy Arditi, Oscar Obeso, Aaquib Syed, Daniel Paleka, Nina Panickssery, Wes Gurnee, and Neel Nanda. 2024 · 2024

Cited alongside, same era.

Language Models are Homer Simpson! Safety Re-Alignment of Fine-tuned Language Models through Task Arithmetic

Rishabh Bhardwaj, Do Duc Anh, and Soujanya Poria. 2024 · 2024

Cited alongside, same era.

Defending against alignment-breaking attacks via robustly aligned LLM

Bochuan Cao, Yuanpu Cao, Lu Lin, and Jinghui Chen. 2024 · 2024

Cited alongside, same era.

Safety alignment should be made more than just a few tokens deep

Original

Xiangyu Qi, Ashwinee Panda, Kaifeng Lyu, Xiao Ma, Subhrajit Roy, Ahmad Beirami, Prateek Mittal, and Peter Henderson. 2024 · 2024

Later among the works it cites.

Direct preference optimization: Your language model is secretly a reward model

Original

Rafael Rafailov, Archit Sharma, Eric Mitchell, Stefano Ermon, Christopher D. Manning, and Chelsea Finn. 2024 · 2024

Later among the works it cites.

Smoothllm: Defending large language models against jailbreaking attacks

Original

Alexander Robey, Eric Wong, Hamed Hassani, and George J. Pappas. 2024 · 2024

Later among the works it cites.

Immunization against harmful fine-tuning attacks

Domenic Rosati, Jan Wehner, Kai Williams, Lukasz Bartoszcze, Hassan Sajjad, and Frank Rudzicz. 2024 · 2024

Later among the works it cites.

Deepseekmath: Pushing the limits of mathematical reasoning in open language models