Scaling Laws for Reward Model Overoptimization

19 October 2022

Papers citing "Scaling Laws for Reward Model Overoptimization"

39 / 89 papers shown

Title
Catastrophic Goodhart: regularizing RLHF with KL divergence does not mitigate heavy-tailed reward misspecification Thomas Kwa Drake Thomas Adrià Garriga-Alonso 16 1 0 19 Jul 2024
Variational Best-of-N Alignment Afra Amini Tim Vieira Ryan Cotterell Ryan Cotterell BDL 43 18 0 08 Jul 2024
WARP: On the Benefits of Weight Averaged Rewarded Policies Alexandre Ramé Johan Ferret Nino Vieillard Robert Dadashi Léonard Hussenot Pierre-Louis Cedoz Pier Giuseppe Sessa Sertan Girgin Arthur Douillard Olivier Bachem 47 13 0 24 Jun 2024
On the Transformations across Reward Model, Parameter Update, and In-Context Prompt Deng Cai Huayang Li Tingchen Fu Siheng Li Weiwen Xu ... Leyang Cui Yan Wang Lemao Liu Taro Watanabe Shuming Shi KELM 26 2 0 24 Jun 2024
SPA-VL: A Comprehensive Safety Preference Alignment Dataset for Vision Language Model Yongting Zhang Lu Chen Guodong Zheng Yifeng Gao Rui Zheng ... Yu Qiao Xuanjing Huang Feng Zhao Tao Gui Jing Shao VLM 75 23 0 17 Jun 2024
Humor in AI: Massive Scale Crowd-Sourced Preferences and Benchmarks for Cartoon Captioning Jifan Zhang Lalit P. Jain Yang Guo Jiayi Chen Kuan Lok Zhou ... Scott Sievert Timothy Rogers Kevin Jamieson Robert Mankoff Robert Nowak 29 5 0 15 Jun 2024
Regularizing Hidden States Enables Learning Generalizable Reward Model for LLMs Rui Yang Ruomeng Ding Yong Lin Huan Zhang Tong Zhang 21 42 0 14 Jun 2024
How to Strategize Human Content Creation in the Era of GenAI? Seyed A. Esmaeili Kshipra Bhawalkar Zhe Feng Di Wang Di Wang Haifeng Xu 43 3 0 07 Jun 2024
Stratified Prediction-Powered Inference for Hybrid Language Model Evaluation Adam Fisch Joshua Maynez R. A. Hofer Bhuwan Dhingra Amir Globerson William W. Cohen 34 7 0 06 Jun 2024
TS-Align: A Teacher-Student Collaborative Framework for Scalable Iterative Finetuning of Large Language Models Chen Zhang Chengguang Tang Dading Chong Ke Shi Guohua Tang Feng Jiang Haizhou Li 27 4 0 30 May 2024
Enhancing Large Vision Language Models with Self-Training on Image Comprehension Yihe Deng Pan Lu Fan Yin Ziniu Hu Sheng Shen James Y. Zou Kai-Wei Chang Wei Wang SyDa VLM LRM 31 36 0 30 May 2024
One-Shot Safety Alignment for Large Language Models via Optimal Dualization Xinmeng Huang Shuo Li Edgar Dobriban Osbert Bastani Hamed Hassani Dongsheng Ding 36 3 0 29 May 2024
Offline Regularised Reinforcement Learning for Large Language Models Alignment Pierre Harvey Richemond Yunhao Tang Daniel Guo Daniele Calandriello M. G. Azar ... Gil Shamir Rishabh Joshi Tianqi Liu Rémi Munos Bilal Piot OffRL 40 21 0 29 May 2024
Alleviating Hallucinations in Large Vision-Language Models through Hallucination-Induced Optimization Beitao Chen Xinyu Lyu Lianli Gao Jingkuan Song Hengtao Shen MLLM 49 10 0 24 May 2024
Understanding the performance gap between online and offline alignment algorithms Yunhao Tang Daniel Guo Zeyu Zheng Daniele Calandriello Yuan Cao ... Rémi Munos Bernardo Avila-Pires Michal Valko Yong Cheng Will Dabney OffRL OnRL 25 61 0 14 May 2024
Learn Your Reference Model for Real Good Alignment Alexey Gorbatovski Boris Shaposhnikov Alexey Malakhov Nikita Surnachev Yaroslav Aksenov Ian Maksimov Nikita Balagansky Daniil Gavrilov OffRL 47 25 0 15 Apr 2024
Reinforcement Learning from Human Feedback with Active Queries Kaixuan Ji Jiafan He Quanquan Gu 8 17 0 14 Feb 2024
Generalized Preference Optimization: A Unified Approach to Offline Alignment Yunhao Tang Z. Guo Zeyu Zheng Daniele Calandriello Rémi Munos Mark Rowland Pierre Harvey Richemond Michal Valko Bernardo Avila-Pires Bilal Piot 32 85 0 08 Feb 2024
Iterative Data Smoothing: Mitigating Reward Overfitting and Overoptimization in RLHF Banghua Zhu Michael I. Jordan Jiantao Jiao 21 22 0 29 Jan 2024
Theoretical guarantees on the best-of-n alignment policy Ahmad Beirami Alekh Agarwal Jonathan Berant Alex DÁmour Jacob Eisenstein Chirag Nagpal A. Suresh 42 42 0 03 Jan 2024
Aligning Human Intent from Imperfect Demonstrations with Confidence-based Inverse soft-Q Learning Xizhou Bu Wenjuan Li Zhengxiong Liu Zhiqiang Ma Panfeng Huang 20 1 0 18 Dec 2023
Towards Understanding Sycophancy in Language Models Mrinank Sharma Meg Tong Tomasz Korbak D. Duvenaud Amanda Askell ... Oliver Rausch Nicholas Schiefer Da Yan Miranda Zhang Ethan Perez 209 178 0 20 Oct 2023
Constructive Large Language Models Alignment with Diverse Feedback Tianshu Yu Ting-En Lin Yuchuan Wu Min Yang Fei Huang Yongbin Li ALM 30 8 0 10 Oct 2023
Generative Judge for Evaluating Alignment Junlong Li Shichao Sun Weizhe Yuan Run-Ze Fan Hai Zhao Pengfei Liu ELM ALM 12 76 0 09 Oct 2023
Beyond Reverse KL: Generalizing Direct Preference Optimization with Diverse Divergence Constraints Chaoqi Wang Yibo Jiang Yuguang Yang Han Liu Yuxin Chen 19 81 0 28 Sep 2023
The Trickle-down Impact of Reward (In-)consistency on RLHF Lingfeng Shen Sihao Chen Linfeng Song Lifeng Jin Baolin Peng Haitao Mi Daniel Khashabi Dong Yu 18 21 0 28 Sep 2023
LLQL: Logistic Likelihood Q-Learning for Reinforcement Learning Outongyi Lv Bingxin Zhou OffRL 21 0 0 05 Jul 2023
Let Me Teach You: Pedagogical Foundations of Feedback for Language Models Beatriz Borges Niket Tandon Tanja Kaser Antoine Bosselut 17 3 0 01 Jul 2023
Reinforcement Learning with Human Feedback: Learning Dynamic Choices via Pessimism Zihao Li Zhuoran Yang Mengdi Wang OffRL 24 51 0 29 May 2023
RAFT: Reward rAnked FineTuning for Generative Foundation Model Alignment Hanze Dong Wei Xiong Deepanshu Goyal Yihan Zhang Winnie Chow Rui Pan Shizhe Diao Jipeng Zhang Kashun Shum Tong Zhang ALM 6 397 0 13 Apr 2023
Training Language Models with Language Feedback at Scale Jérémy Scheurer Jon Ander Campos Tomasz Korbak Jun Shern Chan Angelica Chen Kyunghyun Cho Ethan Perez ALM 29 101 0 28 Mar 2023
CodeLMSec Benchmark: Systematically Evaluating and Finding Security Vulnerabilities in Black-Box Code Language Models Hossein Hajipour Keno Hassler Thorsten Holz Lea Schonherr Mario Fritz ELM 25 19 0 08 Feb 2023
Reward Gaming in Conditional Text Generation Richard Yuanzhe Pang Vishakh Padmakumar Thibault Sellam Ankur P. Parikh He He 21 24 0 16 Nov 2022
Improving alignment of dialogue agents via targeted human judgements Amelia Glaese Nat McAleese Maja Trkebacz John Aslanides Vlad Firoiu ... John F. J. Mellor Demis Hassabis Koray Kavukcuoglu Lisa Anne Hendricks G. Irving ALM AAML 225 495 0 28 Sep 2022
Defining and Characterizing Reward Hacking Joar Skalse Nikolaus H. R. Howe Dmitrii Krasheninnikov David M. Krueger 57 53 0 27 Sep 2022
Teaching language models to support answers with verified quotes Jacob Menick Maja Trebacz Vladimir Mikulik John Aslanides Francis Song ... Mia Glaese Susannah Young Lucy Campbell-Gillingham G. Irving Nat McAleese ELM RALM 229 255 0 21 Mar 2022
Training language models to follow instructions with human feedback Long Ouyang Jeff Wu Xu Jiang Diogo Almeida Carroll L. Wainwright ... Amanda Askell Peter Welinder Paul Christiano Jan Leike Ryan J. Lowe OSLM ALM 303 11,730 0 04 Mar 2022
Gradient-based Adversarial Attacks against Text Transformers Chuan Guo Alexandre Sablayrolles Hervé Jégou Douwe Kiela SILM 98 225 0 15 Apr 2021
Scaling Laws for Neural Language Models Jared Kaplan Sam McCandlish T. Henighan Tom B. Brown B. Chess R. Child Scott Gray Alec Radford Jeff Wu Dario Amodei 226 4,424 0 23 Jan 2020