English
Related papers

Related papers: PIPA: Preference Alignment as Prior-Informed Stati…

200 papers

Direct Preference Optimization (DPO), a standard method for aligning language models with human preferences, is traditionally applied to offline preferences. Recent studies show that DPO benefits from iterative training with online…

Computation and Language · Computer Science 2024-06-18 Jie Liu , Zhanhui Zhou , Jiaheng Liu , Xingyuan Bu , Chao Yang , Han-Sen Zhong , Wanli Ouyang

Direct Preference Optimization (DPO) has emerged as a compelling approach for training Large Language Models (LLMs) to adhere to human preferences. However, the performance of DPO is sensitive to the fine-tuning of its trade-off parameter…

Artificial Intelligence · Computer Science 2024-10-15 Junkang Wu , Yuexiang Xie , Zhengyi Yang , Jiancan Wu , Jinyang Gao , Bolin Ding , Xiang Wang , Xiangnan He

In this paper, we introduce \emph{refined Direct Preference Optimization} (rDPO), a method for improving the behavioral alignment of Large Language Models (LLMs) without the need for human-annotated data. The method involves creating…

Computation and Language · Computer Science 2024-02-14 Víctor Gallego

Direct alignment methods are increasingly used for aligning large language models (LLMs) with human preferences. However, these methods suffer from the issues of verbosity and likelihood displacement, which can be driven by the noisy…

Computation and Language · Computer Science 2025-10-28 Peter Chen , Xi Chen , Wotao Yin , Tianyi Lin

Large language models (LLMs), despite their extensive pretraining on diverse datasets, require effective alignment to human preferences for practical and reliable deployment. Conventional alignment methods typically employ off-policy…

Computation and Language · Computer Science 2025-07-29 Hyeonji Lee , Daejin Jo , Seohwan Yun , Sungwoong Kim

Existing preference datasets for text-to-image models typically store only the final winner/loser images. This representation is insufficient for rectified flow (RF) models, whose generation is naturally indexed by a specific prior noise…

Computer Vision and Pattern Recognition · Computer Science 2026-05-12 Yunhong Lu , Qichao Wang , Hengyuan Cao , Xiaoyin Xu , Min Zhang

Improving the alignment of language models with human preferences remains an active research challenge. Previous approaches have primarily utilized Reinforcement Learning from Human Feedback (RLHF) via online RL methods such as Proximal…

Computation and Language · Computer Science 2024-01-25 Tianqi Liu , Yao Zhao , Rishabh Joshi , Misha Khalman , Mohammad Saleh , Peter J. Liu , Jialu Liu

Aligning language models to human expectations, e.g., being helpful and harmless, has become a pressing challenge for large language models. A typical alignment procedure consists of supervised fine-tuning and preference learning. Most…

Machine Learning · Computer Science 2024-02-27 Tianchi Cai , Xierui Song , Jiyan Jiang , Fei Teng , Jinjie Gu , Guannan Zhang

Multi-preference optimization enriches language-model alignment beyond pairwise preferences by contrasting entire sets of helpful and undesired responses, thereby enabling richer training signals for large language models. During self-play…

Machine Learning · Computer Science 2025-06-10 Taneesh Gupta , Rahul Madhavan , Xuchao Zhang , Chetan Bansal , Saravan Rajmohan

Multi-objective preference alignment of large language models (LLMs) is critical for developing AI systems that are more configurable, personalizable, helpful, and safe. However, optimizing model outputs to satisfy diverse objectives with…

Computation and Language · Computer Science 2025-03-04 Raghav Gupta , Ryan Sullivan , Yunxuan Li , Samrat Phatale , Abhinav Rastogi

Model fusion combines multiple Large Language Models (LLMs) with different strengths into a more powerful, integrated model through lightweight training methods. Existing works on model fusion focus primarily on supervised fine-tuning…

Machine Learning · Computer Science 2026-05-26 Yanggan Gu , Yuanyi Wang , Zhaoyi Yan , Yiming Zhang , Qi Zhou , Fei Wu , Hongxia Yang

Though reasoning abilities are considered language-agnostic, existing LLMs exhibit inconsistent reasoning abilities across different languages, e.g., reasoning in the dominant language like English is superior to other languages due to the…

Computation and Language · Computer Science 2024-04-16 Shuaijie She , Wei Zou , Shujian Huang , Wenhao Zhu , Xiang Liu , Xiang Geng , Jiajun Chen

Aligning Large Language Models (LLMs) with human preferences is crucial, but standard methods like Reinforcement Learning from Human Feedback (RLHF) are often complex and unstable. In this work, we propose a new, simpler approach that…

Machine Learning · Computer Science 2026-01-27 Saeed Najafi , Alona Fyshe

Direct Preference Optimization (DPO) have emerged as a popular method for aligning Large Language Models (LLMs) with human preferences. While DPO effectively preserves the relative ordering between chosen and rejected responses through…

Computation and Language · Computer Science 2025-06-05 Lin Sun , Chuang Liu , Peng Liu , Bingyang Li , Weijia Lu , Ning Wu

Direct Preference Optimization (DPO) is a widely adopted offline algorithm for preference-based reinforcement learning from human feedback (RLHF), designed to improve training simplicity and stability by redefining reward functions.…

Computation and Language · Computer Science 2025-05-30 Gengxu Li , Tingyu Xia , Yi Chang , Yuan Wu

Large Language Models (LLMs) have become increasingly popular due to their ability to process and generate natural language. However, as they are trained on massive datasets of text, LLMs can inherit harmful biases and produce outputs that…

Computation and Language · Computer Science 2025-01-23 Qi Gou , Cam-Tu Nguyen

Multi-Objective Alignment (MOA) aims to align LLMs' responses with multiple human preference objectives, with Direct Preference Optimization (DPO) emerging as a prominent approach. However, we find that DPO-based MOA approaches suffer from…

Machine Learning · Computer Science 2025-12-09 Moxin Li , Yuantao Zhang , Wenjie Wang , Wentao Shi , Zhuo Liu , Fuli Feng , Tat-Seng Chua

Direct Preference Optimization (DPO) improves the alignment of large language models (LLMs) with human values by training directly on human preference datasets, eliminating the need for reward models. However, due to the presence of…

Artificial Intelligence · Computer Science 2024-06-11 Biqing Qi , Pengfei Li , Fangyuan Li , Junqi Gao , Kaiyan Zhang , Bowen Zhou

Preference Optimization (PO), is gaining popularity as an alternative choice of Proximal Policy Optimization (PPO) for aligning Large Language Models (LLMs). Recent research on aligning LLMs iteratively with synthetic or partially synthetic…

Computation and Language · Computer Science 2024-09-16 Yaojie Shen , Xinyao Wang , Yulei Niu , Ying Zhou , Lexin Tang , Libo Zhang , Fan Chen , Longyin Wen

Preference learning is a key technology for aligning language models with human values. Reinforcement Learning from Human Feedback (RLHF) is a model-based algorithm to optimize preference learning, which first fits a reward model for…

Machine Learning · Computer Science 2024-03-26 Zaifan Jiang , Xing Huang , Chao Wei