English
Related papers

Related papers: Preference learning made easy: Everything should b…

200 papers

One of the challenges of aligning large models with human preferences lies in both the data requirements and the technical complexities of current approaches. Predominant methods, such as RLHF, involve multiple steps, each demanding…

Machine Learning · Computer Science 2025-03-19 Siliang Zeng , Yao Liu , Huzefa Rangwala , George Karypis , Mingyi Hong , Rasool Fakoor

Direct preference optimization (DPO) is a form of reinforcement learning from human feedback (RLHF) where the policy is learned directly from preferential feedback. Although many models of human preferences exist, the critical task of…

Machine Learning · Computer Science 2025-03-04 Branislav Kveton , Xintong Li , Julian McAuley , Ryan Rossi , Jingbo Shang , Junda Wu , Tong Yu

Despite the parallel challenges that audio and text domains face in evaluating generative model outputs, preference learning remains remarkably underexplored in audio applications. Through a PRISMA-guided systematic review of approximately…

Sound · Computer Science 2025-11-19 Aaron Broukhim , Yiran Shen , Prithviraj Ammanabrolu , Nadir Weibel

Direct Preference Optimization (DPO) has emerged as a simple and effective approach for aligning large language models (LLMs) with human preferences, bypassing the need for a learned reward model. Despite its growing adoption, a fundamental…

Machine Learning · Computer Science 2025-11-10 Yu Pan , Zhongze Cai , Guanting Chen , Huaiyang Zhong , Chonghuan Wang

Direct Preference Optimization (DPO) trains a language model using human preference data, bypassing the explicit reward modeling phase of Reinforcement Learning from Human Feedback (RLHF). By iterating over sentence pairs in a preference…

Machine Learning · Computer Science 2024-10-31 Jae Hyeon Cho , Minkyung Park , Byung-Jun Lee

Diffusion models have made substantial advances in image generation, yet models trained on large, unfiltered datasets often yield outputs misaligned with human preferences. Numerous methods have been proposed to fine-tune pre-trained…

Computer Vision and Pattern Recognition · Computer Science 2025-05-19 Fu-Yun Wang , Yunhao Shui , Jingtan Piao , Keqiang Sun , Hongsheng Li

Preferences within a group of people are not uniform but follow a distribution. While existing alignment methods like Direct Preference Optimization (DPO) attempt to steer models to reflect human preferences, they struggle to capture the…

Computation and Language · Computer Science 2025-05-14 Binwei Yao , Zefan Cai , Yun-Shiuan Chuang , Shanglin Yang , Ming Jiang , Diyi Yang , Junjie Hu

Eliciting preferences from human judgements is inherently imprecise, yet most decision analysis methods force a single priority vector from pairwise comparisons, discarding the information embedded in inconsistencies. We instead leverage…

General Economics · Economics 2026-02-27 Salvatore Greco , Sajid Siraj , Michele Lundy

We propose a new framework for imitation learning -- treating imitation as a two-player ranking-based game between a policy and a reward. In this game, the reward agent learns to satisfy pairwise performance rankings between behaviors,…

Machine Learning · Computer Science 2023-01-18 Harshit Sikchi , Akanksha Saran , Wonjoon Goo , Scott Niekum

Learning from human feedback (LHF) -- and in particular learning from pairwise preferences -- has recently become a crucial ingredient in training large language models (LLMs), and has been the subject of much research. Most recent works…

Machine Learning · Computer Science 2024-01-11 Vincent Dumoulin , Daniel D. Johnson , Pablo Samuel Castro , Hugo Larochelle , Yann Dauphin

Traditional RLHF-based LLM alignment methods explicitly maximize the expected rewards from a separate reward model. More recent supervised alignment methods like Direct Preference Optimization (DPO) circumvent this phase to avoid problems…

Machine Learning · Computer Science 2025-02-03 Abhijnan Nath , Changsoo Jung , Ethan Seefried , Nikhil Krishnaswamy

The class of direct preference optimization (DPO) algorithms has emerged as a promising approach for solving the alignment problem in foundation models. These algorithms work with very limited feedback in the form of pairwise preferences…

Machine Learning · Computer Science 2026-02-03 Luca Viano , Ruida Zhou , Yifan Sun , Mahdi Namazifar , Volkan Cevher , Shoham Sabach , Mohammad Ghavamzadeh

Reinforcement learning from human feedback (RLHF) is a promising solution to align large language models (LLMs) more closely with human values. Off-policy preference optimization, where the preference data is obtained from other models, is…

Computation and Language · Computer Science 2024-10-07 Wenxuan Zhou , Ravi Agrawal , Shujian Zhang , Sathish Reddy Indurthi , Sanqiang Zhao , Kaiqiang Song , Silei Xu , Chenguang Zhu

Direct Preference Optimization (DPO), which derives reward signals directly from pairwise preference data, has shown its effectiveness on aligning Large Language Models (LLMs) with human preferences. Despite its widespread use across…

Computation and Language · Computer Science 2024-04-09 Duanyu Feng , Bowen Qin , Chen Huang , Zheng Zhang , Wenqiang Lei

In this paper, we take a step towards a deeper understanding of learning from human preferences by systematically comparing the paradigm of reinforcement learning from human feedback (RLHF) with the recently proposed paradigm of direct…

Machine Learning · Computer Science 2024-06-06 Andi Nika , Debmalya Mandal , Parameswaran Kamalaruban , Georgios Tzannetos , Goran Radanović , Adish Singla

Conventional preference learning methods often prioritize opinions held more widely when aggregating preferences from multiple evaluators. This may result in policies that are biased in favor of some types of opinions or groups and…

Artificial Intelligence · Computer Science 2026-03-03 Kihyun Kim , Jiawei Zhang , Asuman Ozdaglar , Pablo A. Parrilo

Reinforcement Learning from Human Feedback (RLHF) has emerged as a powerful approach for aligning generative models, but its reliance on learned reward models makes it vulnerable to mis-specification and reward hacking. Preference-based…

Machine Learning · Computer Science 2026-04-23 Akhil Agnihotri , Rahul Jain , Deepak Ramachandran , Zheng Wen

Preference-based reward learning is a popular technique for teaching robots and autonomous systems how a human user wants them to perform a task. Previous works have shown that actively synthesizing preference queries to maximize…

Robotics · Computer Science 2024-03-12 Evan Ellis , Gaurav R. Ghosal , Stuart J. Russell , Anca Dragan , Erdem Bıyık

Language model (LM) post-training (or alignment) involves maximizing a reward function that is derived from preference annotations. Direct Preference Optimization (DPO) is a popular offline alignment method that trains a policy directly on…

Machine Learning · Computer Science 2025-03-04 Adam Fisch , Jacob Eisenstein , Vicky Zayats , Alekh Agarwal , Ahmad Beirami , Chirag Nagpal , Pete Shaw , Jonathan Berant

Recently, preference optimization methods such as DPO have significantly enhanced large language models (LLMs) in wide tasks including dialogue and question-answering. However, current methods fail to account for the varying difficulty…

Computation and Language · Computer Science 2024-12-31 Jingyuan Ma , Rui Li , Zheng Li , Lei Sha , Zhifang Sui