English
Related papers

Related papers: Anchored Preference Optimization and Contrastive R…

200 papers

Direct Preference Optimization (DPO) is an effective technique that leverages pairwise preference data (usually one chosen and rejected response pair per user prompt) to align LLMs to human preferences. In practice, multiple responses can…

Computation and Language · Computer Science 2024-11-11 Pulkit Pattnaik , Rishabh Maheshwary , Kelechi Ogueji , Vikas Yadav , Sathwik Tejaswi Madhusudhan

Preference learning algorithms (e.g., RLHF and DPO) are frequently used to steer LLMs to produce generations that are more preferred by humans, but our understanding of their inner workings is still limited. In this work, we study the…

Machine Learning · Computer Science 2024-11-01 Angelica Chen , Sadhika Malladi , Lily H. Zhang , Xinyi Chen , Qiuyi Zhang , Rajesh Ranganath , Kyunghyun Cho

Large Vision-Language Models (LVLMs) have shown promising capabilities in understanding and generating information by integrating both visual and textual data. However, current models are still prone to hallucinations, which degrade the…

Computer Vision and Pattern Recognition · Computer Science 2025-11-13 Robert Wijaya , Ngoc-Bao Nguyen , Ngai-Man Cheung

Preference alignment has achieved greater success on Large Language Models (LLMs) and drawn broad interest in recommendation research. Existing preference alignment methods for recommendation either require explicit reward modeling or only…

Information Retrieval · Computer Science 2025-07-04 Zihao Li , Chao Yang , Tong Zhang , Yakun Chen , Xianzhi Wang , Guandong Xu , Daoyi Dong

Preference learning is critical for aligning large language models (LLMs) with human values, yet its success hinges on high-quality datasets comprising three core components: Preference \textbf{A}nnotations, \textbf{I}nstructions, and…

Computation and Language · Computer Science 2025-09-03 Bingxiang He , Wenbin Zhang , Jiaxi Song , Cheng Qian , Zixuan Fu , Bowen Sun , Ning Ding , Haiwen Hong , Longtao Huang , Hui Xue , Ganqu Cui , Wanxiang Che , Zhiyuan Liu , Maosong Sun

The dominant framework for alignment of large language models (LLM), whether through reinforcement learning from human feedback or direct preference optimisation, is to learn from preference data. This involves building datasets where each…

Large Vision-Language Models (LVLMs) hold immense potential for complex multimodal instruction following, yet their development is often hindered by the high cost and inconsistency of human annotation required for effective fine-tuning and…

Computation and Language · Computer Science 2025-08-19 Ruirui Gao , Emily Johnson , Bowen Tan , Yanfei Qian

In real-world services such as ChatGPT, aligning models based on user feedback is crucial for improving model performance. However, due to the simplicity and convenience of providing feedback, users typically offer only basic binary…

Machine Learning · Computer Science 2025-06-10 Seungjae Jung , Gunsoo Han , Daniel Wontae Nam , Kyoung-Woon On

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

The recent success in using human preferences to align large language models (LLMs) has significantly improved their performance in various downstream tasks, such as question answering, mathematical reasoning, and code generation. However,…

Machine Learning · Computer Science 2026-05-18 Xiaoqiang Lin , Arun Verma , Zhongxiang Dai , Daniela Rus , See-Kiong Ng , Bryan Kian Hsiang Low

Modern language models often rely on Reinforcement Learning from Human Feedback (RLHF) to encourage safe behaviors. However, they remain vulnerable to adversarial attacks due to three key limitations: (1) the inefficiency and high cost of…

Large Language Models (LLMs) still produce gender-stereotyped language even in occupation-neutral contexts that reflect deep societal biases (Rudinger et al., 2018). To address this, prior work has proposed prompting, constrained decoding…

Computation and Language · Computer Science 2025-10-28 Atij Mahesh

Accurately aligning large language models (LLMs) with human preferences is crucial for informing fair, economically sound, and statistically efficient decision-making processes. However, we argue that the predominant approach for aligning…

Machine Learning · Statistics 2025-08-26 Jiancong Xiao , Ziniu Li , Xingyu Xie , Emily Getzen , Cong Fang , Qi Long , Weijie J. Su

Alignment of large language models (LLMs) with human values has recently garnered significant attention, with prominent examples including the canonical yet costly Reinforcement Learning from Human Feedback (RLHF) and the simple Direct…

Machine Learning · Computer Science 2025-10-14 Xufei Lv , Kehai Chen , Haoyuan Sun , Xuefeng Bai , Min Zhang , Houde Liu , Kehai Chen

Reinforcement Learning from Human Feedback (RLHF) has emerged as a powerful technique for aligning large language models (LLMs) with human preferences. However, effectively aligning LLMs with diverse human preferences remains a significant…

Computation and Language · Computer Science 2025-07-03 Chengao Li , Hanyu Zhang , Yunkun Xu , Hongyan Xue , Xiang Ao , Qing He

Learning from preference labels plays a crucial role in fine-tuning large language models. There are several distinct approaches for preference fine-tuning, including supervised learning, on-policy reinforcement learning (RL), and…

Preference finetuning methods like Direct Preference Optimization (DPO) with AI-generated feedback have shown promise in aligning Large Vision-Language Models (LVLMs) with human preferences. However, existing techniques overlook the…

Artificial Intelligence · Computer Science 2025-10-03 Rohan Wadhawan , Fabrice Y Harel-Canada , Zi-Yi Dou , Suhaila Shakiah , Robinson Piramuthu , Nanyun Peng

Recently, Large Language Models (LLMs) have rapidly evolved, approaching Artificial General Intelligence (AGI) while benefiting from large-scale reinforcement learning to enhance Human Alignment (HA) and Reasoning. Recent reward-based…

Machine Learning · Computer Science 2025-06-19 Xuerui Su , Shufang Xie , Guoqing Liu , Yingce Xia , Renqian Luo , Peiran Jin , Zhiming Ma , Yue Wang , Zun Wang , Yuting Liu

As large language models (LLMs) are increasingly used as evaluators for natural language generation tasks, ensuring unbiased assessments is essential. However, LLM evaluators often display biased preferences, such as favoring verbosity and…

Computation and Language · Computer Science 2025-04-21 Hawon Jeong , ChaeHun Park , Jimin Hong , Hojoon Lee , Jaegul Choo

Preference alignment through Direct Preference Optimization (DPO) has demonstrated significant effectiveness in aligning multimodal large language models (MLLMs) with human preferences. However, existing methods focus primarily on language…

Computer Vision and Pattern Recognition · Computer Science 2025-04-23 Jinda Lu , Jinghan Li , Yuan Gao , Junkang Wu , Jiancan Wu , Xiang Wang , Xiangnan He