Fetching the paper…
Reading the bibliography…
Direct Alignment Algorithms (DAAs), such as Direct Preference Optimisation (DPO) and Identity Preference Optimisation (IPO), have emerged as alternatives to online Reinforcement Learning from Human Feedback (RLHF) algorithms such as Proximal Policy Optimisation (PPO) for aligning language models to human preferences, without the need for explicit reward modelling.
Fine-tuning language models from human preferences
Daniel M Ziegler, Nisan Stiennon, Jeffrey Wu, Tom B Brown, Alec Radford, Dario Amodei, Paul Christiano, and Geoffrey Irving · 1909
Earlier work this paper cites.
Robust estimation of a location parameter
Peter J Huber · 1992
Earlier work this paper cites.
An introduction to support vector machines and other kernel-based learning methods
Nello Cristianini and John Shawe-Taylor · 2000
Earlier work this paper cites.
Adam: A method for stochastic optimization
Diederik P Kingma · 2014
Earlier work this paper cites.
A diversity-promoting objective function for neural conversation models
Jiwei Li, Michel Galley, Chris Brockett, Jianfeng Gao, and Bill Dolan · 2016
Earlier work this paper cites.
Asynchronous methods for deep reinforcement learning
Volodymyr Mnih · 2016
Earlier work this paper cites.
Deep reinforcement learning from human preferences
Paul F Christiano, Jan Leike, Tom Brown, Miljan Martic, Shane Legg, and Dario Amodei · 2017
Earlier work this paper cites.
triviaqa: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension
Mandar Joshi, Eunsol Choi, Daniel Weld, and Luke Zettlemoyer · 2017
Earlier work this paper cites.
Proximal policy optimization algorithms
John Schulman, Filip Wolski, Prafulla Dhariwal, Alec Radford, and Oleg Klimov · 2017
Earlier work this paper cites.
Attention is all you need
Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Ł ukasz Kaiser, and Illia Polosukhin · 2017
Earlier work this paper cites.
Natural questions: A benchmark for question answering research
Tom Kwiatkowski, Jennimaria Palomaki, Olivia Redfield, Michael Collins, Ankur Parikh, Chris Alberti, Danielle Epstein, Illia Polosukhin, Jacob Devlin, Kenton Lee, Kristina Toutanova, Llion Jones, Matthew Kelcey, Ming-Wei Chang, Andrew M. Dai, Jakob Uszkoreit, Quoc Le, and Slav Petrov · 2019
Earlier work this paper cites.
Pretrained transformers improve out-of-distribution robustness
Dan Hendrycks, Xiaoyuan Liu, Eric Wallace, Adam Dziedzic, Rishabh Krishnan, and Dawn Song · 2020
Earlier work this paper cites.
Learning to summarize with human feedback
Nisan Stiennon, Long Ouyang, Jeffrey Wu, Daniel Ziegler, Ryan Lowe, Chelsea Voss, Alec Radford, Dario Amodei, and Paul F Christiano · 2020
Earlier work this paper cites.
A survey of code-switching: Linguistic and social perspectives for language technologies
A. Seza Doğruöz, Sunayana Sitaram, Barbara E. Bullock, and Almeida Jacqueline Toribio · 2021
Earlier work this paper cites.
A distributional approach to controlled text generation
Muhammad Khalifa, Hady Elsahar, and Marc Dymetman · 2021
Earlier work this paper cites.
Training a helpful and harmless assistant with reinforcement learning from human feedback
Yuntao Bai, Andy Jones, Kamal Ndousse, Amanda Askell, Anna Chen, Nova DasSarma, Dawn Drain, Stanislav Fort, Deep Ganguli, Tom Henighan, et al · 2022
Earlier work this paper cites.
Flashattention: Fast and memory-efficient exact attention with io-awareness
Tri Dao, Dan Fu, Stefano Ermon, Atri Rudra, and Christopher Ré · 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, John Schulman, Jacob Hilton, Fraser Kelton, Luke Miller, Maddie Simens, Amanda Askell, Peter Welinder, Paul F Christiano, Jan Leike, and Ryan Lowe · 2022
Earlier work this paper cites.
Red teaming language models with language models
Ethan Perez, Saffron Huang, Francis Song, Trevor Cai, Roman Ring, John Aslanides, Amelia Glaese, Nat McAleese, and Geoffrey Irving · 2022
Earlier work this paper cites.
Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al · 2023
Earlier work this paper cites.
Jinze Bai, Shuai Bai, Yunfei Chu, Zeyu Cui, Kai Dang, Xiaodong Deng, Yang Fan, Wenbin Ge, Yu Han, Fei Huang, et al · 2023
Earlier work this paper cites.
Alpacafarm: A simulation framework for methods that learn from human feedback
Yann Dubois, Chen Xuechen Li, Rohan Taori, Tianyi Zhang, Ishaan Gulrajani, Jimmy Ba, Carlos Guestrin, Percy S Liang, and Tatsunori B Hashimoto · 2023
Cited alongside, same era.
Helping or herding? reward model ensembles mitigate but do not eliminate reward hacking
Jacob Eisenstein, Chirag Nagpal, Alekh Agarwal, Ahmad Beirami, Alex D’Amour, DJ Dvijotham, Adam Fisch, Katherine Heller, Stephen Pfohl, Deepak Ramachandran, et al · 2023
Cited alongside, same era.
Scaling laws for reward model overoptimization
Leo Gao, John Schulman, and Jacob Hilton · 2023
Cited alongside, same era.
Can llms learn from a single example?, 2023
Jeremy Howard and Jonathan Whitaker · 2023
Cited alongside, same era.
Understanding catastrophic forgetting in language models via implicit inference
Suhas Kotha, Jacob Mitchell Springer, and Aditi Raghunathan · 2023
Cited alongside, same era.
claude-3-5-sonnet, 2024
Claude · 2024
Closest in time.
c4ai-command-r-08-2024, 2024
Cohere For AI · 2024
Closest in time.
Reward model ensembles help mitigate overoptimization
Thomas Coste, Usman Anwar, Robert Kirk, and David Krueger · 2024
Closest in time.
Ultrafeedback: Boosting language models with scaled ai feedback
Ganqu Cui, Lifan Yuan, Ning Ding, Guanming Yao, Bingxiang He, Wei Zhu, Yuan Ni, Guotong Xie, Ruobing Xie, Yankai Lin, Zhiyuan Liu, and Maosong Sun · 2024
Closest in time.
Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al-Dahle, Aiesha Letman, Akhil Mathur, Alan Schelten, Amy Yang, Angela Fan, et al · 2024
Closest in time.
Orpo: Monolithic preference optimization without reference model
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
Semantic uncertainty: Linguistic invariances for uncertainty estimation in natural language generation
Lorenz Kuhn, Yarin Gal, and Sebastian Farquhar · 2023
Cited alongside, same era.
Language model alignment with elastic reset
Michael Noukhovitch, Samuel Lavoie, Florian Strub, and Aaron C Courville · 2023
Cited alongside, same era.
Direct preference optimization: Your language model is secretly a reward model
Rafael Rafailov, Archit Sharma, Eric Mitchell, Christopher D Manning, Stefano Ermon, and Chelsea Finn · 2023
Cited alongside, same era.
Code llama: Open foundation models for code
Baptiste Roziere, Jonas Gehring, Fabian Gloeckle, Sten Sootla, Itai Gat, Xiaoqing Ellen Tan, Yossi Adi, Jingyu Liu, Romain Sauvestre, Tal Remez, et al · 2023
Cited alongside, same era.
Don’t stop pretraining? make prompt-based fine-tuning powerful learner
Zhengxiang Shi and Aldo Lipani · 2023
Cited alongside, same era.
Roformer: Enhanced transformer with rotary position embedding
Jianlin Su, Murtadha Ahmed, Yu Lu, Shengfeng Pan, Wen Bo, and Yunfeng Liu · 2023
Cited alongside, same era.
Stanford alpaca: An instruction-following llama model, 2023
Rohan Taori, Ishaan Gulrajani, Tianyi Zhang, Yann Dubois, Xuechen Li, Carlos Guestrin, Percy Liang, and Tatsunori B. Hashimoto · 2023
Cited alongside, same era.
Jiwoo Hong, Noah Lee, and James Thorne · 2024
Closest in time.
Human feedback is not gold standard
Tom Hosking, Phil Blunsom, and Max Bartolo · 2024
Closest in time.
Rewardbench: Evaluating reward models for language modeling
Nathan Lambert, Valentina Pyatkin, Jacob Morrison, LJ Miranda, Bill Yuchen Lin, Khyathi Chandu, Nouha Dziri, Sachin Kumar, Tom Zick, Yejin Choi, Noah A. Smith, and Hannaneh Hajishirzi · 2024
Closest in time.
Fishing for magikarp: Automatically detecting under-trained tokens in large language models
Sander Land and Max Bartolo · 2024
Closest in time.
Understanding and mitigating language confusion in llms
Kelly Marchisio, Wei-Yin Ko, Alexandre Bérard, Théo Dehaze, and Sebastian Ruder · 2024
Closest in time.
Smaug: Fixing failure modes of preference optimisation with dpo-positive
Arka Pal, Deep Karkhanis, Samuel Dooley, Manley Roberts, Siddartha Naidu, and Colin White · 2024
Closest in time.
Iterative reasoning preference optimization
Richard Yuanzhe Pang, Weizhe Yuan, Kyunghyun Cho, He He, Sainbayar Sukhbaatar, and Jason Weston · 2024
Closest in time.
Fine-tuning aligned language models compromises safety, even when users do not intend to!
Xiangyu Qi, Yi Zeng, Tinghao Xie, Pin-Yu Chen, Ruoxi Jia, Prateek Mittal, and Peter Henderson · 2024
Closest in time.
Scaling laws for reward model overoptimization in direct alignment algorithms
Rafael Rafailov, Yaswanth Chittepu, Ryan Park, Harshit Sikchi, Joey Hejna, Bradley Knox, Chelsea Finn, and Scott Niekum · 2024
Closest in time.
DePT: Decomposed prompt tuning for parameter-efficient fine-tuning
Zhengxiang Shi and Aldo Lipani · 2024
Closest in time.
Instruction tuning with loss over instructions
Zhengyan Shi, Adam X Yang, Bin Wu, Laurence Aitchison, Emine Yilmaz, and Aldo Lipani · 2024
Closest in time.
Zephyr: Direct distillation of LM alignment
Lewis Tunstall, Edward Emanuel Beeching, Nathan Lambert, Nazneen Rajani, Kashif Rasul, Younes Belkada, Shengyi Huang, Leandro Von Werra, Clémentine Fourrier, Nathan Habib, Nathan Sarrazin, Omar Sanseviero, Alexander M Rush, and Thomas Wolf · 2024
Closest in time.
Understanding the role of user profile in the personalization of large language models
Bin Wu, Zhengyan Shi, Hossein A Rahmani, Varsha Ramineni, and Emine Yilmaz · 2024
Closest in time.
Improving reward models with synthetic critiques
Zihuiwen Ye, Fraser Greenlee-Scott, Max Bartolo, Phil Blunsom, Jon Ander Campos, and Matthias Gallé · 2024
Closest in time.
Xiaoying Zhang, Jean-Francois Ton, Wei Shen, Hongning Wang, and Yang Liu · 2024
Closest in time.
Iterative data smoothing: Mitigating reward overfitting and overoptimization in RLHF
Banghua Zhu, Michael Jordan, and Jiantao Jiao · 2024
Closest in time.