English
Related papers

Related papers: SeaPO: Strategic Error Amplification for Robust Pr…

200 papers

Aligning large language models (LLMs) with human preferences remains a key challenge in AI. Preference-based optimization methods, such as Reinforcement Learning with Human Feedback (RLHF) and Direct Preference Optimization (DPO), rely on…

Computation and Language · Computer Science 2025-05-26 Xuan Qi , Jiahao Qiu , Xinzhe Juan , Yue Wu , Mengdi Wang

Preference optimization methods such as DPO align large language models (LLMs) using paired comparisons, but their effectiveness can be highly sensitive to the quality and difficulty of preference pairs. A common heuristic treats…

Artificial Intelligence · Computer Science 2026-02-03 Jinlong Pang , Zhaowei Zhu , Na Di , Yichi Zhang , Yaxuan Wang , Chen Qian , Yang Liu

Online and offline RLHF methods, such as PPO and DPO, have been highly successful in aligning AI with human preferences. Despite their success, however, these methods suffer from fundamental limitations: (a) Models trained with RLHF can…

Machine Learning · Computer Science 2025-04-15 Eugene Choi , Arash Ahmadian , Matthieu Geist , Oilvier Pietquin , Mohammad Gheshlaghi Azar

Performance of Large Language Models (LLMs) on multiple-choice tasks differs markedly between symbol-based and cloze-style evaluation formats. The observed discrepancies are systematically attributable to task characteristics: natural…

Computation and Language · Computer Science 2026-02-02 Joonhak Lee , Sungmok Jung , Jongyeon Park , Jaejin Lee

We propose Soft Preference Optimization (SPO), a method for aligning generative models, such as Large Language Models (LLMs), with human preferences, without the need for a reward model. SPO optimizes model outputs directly over a…

Machine Learning · Computer Science 2024-10-07 Arsalan Sharifnassab , Saber Salehkaleybar , Sina Ghiassian , Surya Kanoria , Dale Schuurmans

A significant portion of recent research on Large Language Model (LLM) alignment focuses on developing new policy optimization methods based on Group Relative Policy Optimization (GRPO). Two prominent directions have emerged: (i) a shift…

Machine Learning · Computer Science 2026-02-27 Svetlana Glazyrina , Maksim Kryzhanovskiy , Roman Ischenko

Reinforcement Learning from Human Feedback (RLHF) has emerged as a pivotal technique for large language model (LLM) alignment. This paper studies the setting of online RLHF and focus on improving sample efficiency. All existing algorithms…

Machine Learning · Computer Science 2025-09-29 Mingyu Chen , Yiding Chen , Wen Sun , Xuezhou Zhang

The alignment of large language models with human values presents a critical challenge, particularly when balancing conflicting objectives like helpfulness and harmlessness. Existing approaches, such as Reinforcement Learning from Human…

Computation and Language · Computer Science 2025-03-04 Yuxuan Liu

Aligning large language models (LLMs) depends on high-quality datasets of human preference labels, which are costly to collect. Although active learning has been studied to improve sample efficiency relative to passive collection, many…

Machine Learning · Computer Science 2026-02-03 Yao Zhao , Kwang-Sung Jun

Recent advances in preference optimization have demonstrated significant potential for improving mathematical reasoning capabilities in large language models (LLMs). While current approaches leverage high-quality pairwise preference data…

Computation and Language · Computer Science 2025-05-30 Yunqiao Yang , Houxing Ren , Zimu Lu , Ke Wang , Weikang Shi , Aojun Zhou , Junting Pan , Mingjie Zhan , Hongsheng Li

The growing emotional stress in modern society has increased the demand for Emotional Support Conversations (ESC). While Large Language Models (LLMs) show promise for ESC, they face two key challenges: (1) low strategy selection accuracy,…

Computation and Language · Computer Science 2025-09-22 Weixiang Zhao , Xingyu Sui , Xinyang Han , Yang Deng , Yulin Hu , Jiahe Guo , Libo Qin , Qianyun Du , Shijin Wang , Yanyan Zhao , Bing Qin , Ting Liu

Current large language models (LLMs) generally show a significant performance gap in alignment between English and other languages. To bridge this gap, existing research typically leverages the model's responses in English as a reference to…

Computation and Language · Computer Science 2025-09-16 Xue Zhang , Yunlong Liang , Fandong Meng , Songming Zhang , Yufeng Chen , Jinan Xu , Jie Zhou

Prompt engineering is effective but labor-intensive, motivating automated optimization methods. Existing methods typically require labeled datasets, which are often unavailable, and produce verbose, repetitive prompts. We introduce PrefPO,…

Computation and Language · Computer Science 2026-03-26 Rahul Singhal , Pradyumna Tambwekar , Karime Maamari

Post-training of language models, either through reinforcement learning, preference optimization or supervised finetuning, tends to sharpen the output probability distribution and reduce the diversity of generated responses. This is…

Computation and Language · Computer Science 2025-05-23 Jack Lanchantin , Angelica Chen , Shehzaad Dhuliawala , Ping Yu , Jason Weston , Sainbayar Sukhbaatar , Ilia Kulikov

Reinforcement Learning from Human Feedback (RLHF) has emerged as a pivotal tool for aligning large language models (LLMs) with human preferences. Direct Preference Optimization (DPO), one of the most popular approaches, formulates RLHF as a…

Machine Learning · Computer Science 2024-10-10 Jiafan He , Huizhuo Yuan , Quanquan Gu

Direct Preference Optimization (DPO) is broadly utilized for aligning Large Language Models (LLMs) with human values because of its flexibility. Despite its effectiveness, it has been observed that the capability of DPO to generate…

Machine Learning · Computer Science 2025-05-20 Wenqiao Zhu , Ji Liu , Lulu Wang , Jun Wu , Yulun Zhang

Aligning large language models (LLMs) with human preferences is essential for safe and useful LLMs. Previous works mainly adopt reinforcement learning (RLHF) and direct preference optimization (DPO) with human feedback for alignment.…

Computation and Language · Computer Science 2023-10-03 Tianci Xue , Ziqi Wang , Heng Ji

Large Language Models (LLMs) exhibit remarkably powerful capabilities. One of the crucial factors to achieve success is aligning the LLM's output with human preferences. This alignment process often requires only a small amount of data to…

Reinforcement Learning from Human Feedback (RLHF) is a key method for aligning large language models (LLMs) with human preferences. However, current offline alignment approaches like DPO, IPO, and SLiC rely heavily on fixed preference…

Machine Learning · Computer Science 2024-06-25 Mucong Ding , Souradip Chakraborty , Vibhu Agrawal , Zora Che , Alec Koppel , Mengdi Wang , Amrit Bedi , Furong Huang

Since the release of Deepseek-R1, reinforcement learning with verifiable rewards (RLVR) has become a central approach for training large language models (LLMs) on reasoning tasks. Recent work has largely focused on modifying loss functions…

Machine Learning · Computer Science 2025-10-03 Weizhe Chen , Sven Koenig , Bistra Dilkina