English
Related papers

Related papers: Adaptive Decoding via Latent Preference Optimizati…

200 papers

Instruction following (IF) is a critical capability for large language models (LLMs). However, handling complex instructions with multiple constraints remains challenging. Previous methods typically select preference pairs based on the…

Computation and Language · Computer Science 2025-05-29 Xiang Huang , Ting-En Lin , Feiteng Fang , Yuchuan Wu , Hangyu Li , Yuzhong Qu , Fei Huang , Yongbin Li

Preference optimization has become a central paradigm for aligning large language models with human feedback. Direct Preference Optimization (DPO) simplifies reinforcement learning from human feedback by directly optimizing pairwise…

Machine Learning · Computer Science 2026-05-05 Inoussa Mouiche

Temperature scaling is a popular technique for tuning the sharpness of a model distribution. It is used extensively for sampling likely generations and calibrating model uncertainty, and even features as a controllable parameter to many…

Machine Learning · Computer Science 2023-10-03 Andy Shih , Dorsa Sadigh , Stefano Ermon

The ability of LLMs to represent diverse perspectives is critical as they increasingly impact society. However, recent studies reveal that alignment algorithms such as RLHF and DPO significantly reduce the diversity of LLM outputs. Not only…

Computation and Language · Computer Science 2025-11-13 Stewart Slocum , Asher Parker-Sartori , Dylan Hadfield-Menell

Preference optimization has made significant progress recently, with numerous methods developed to align language models with human preferences. This paper introduces $f$-divergence Preference Optimization ($f$-PO), a novel framework that…

Computation and Language · Computer Science 2025-02-18 Jiaqi Han , Mingjian Jiang , Yuxuan Song , Stefano Ermon , Minkai Xu

Temperature is a widely used hyperparameter in various tasks involving neural networks, such as classification or metric learning, whose choice can have a direct impact on the model performance. Most of existing works select its value using…

Machine Learning · Computer Science 2022-10-19 Benjamin Chamand , Olivier Risser-Maroix , Camille Kurtz , Philippe Joly , Nicolas Loménie

Offline reinforcement learning methods hold the promise of learning policies from pre-collected datasets without the need to query the environment for new transitions. This setting is particularly well-suited for continuous control robotic…

Machine Learning · Computer Science 2022-03-18 Xi Chen , Ali Ghadirzadeh , Tianhe Yu , Yuan Gao , Jianhao Wang , Wenzhe Li , Bin Liang , Chelsea Finn , Chongjie Zhang

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

Vision-language models (VLMs) have made significant progress in image classification by training with large-scale paired image-text data. Their performances largely depend on the prompt quality. While recent methods show that visual…

Computer Vision and Pattern Recognition · Computer Science 2026-02-12 Xiangyan Qu , Gaopeng Gou , Jiamin Zhuang , Jing Yu , Kun Song , Qihao Wang , Yili Li , Gang Xiong

Aligning large language models (LLMs) with human values is an increasingly critical step in post-training. Direct Preference Optimization (DPO) has emerged as a simple, yet effective alternative to reinforcement learning from human feedback…

Artificial Intelligence · Computer Science 2025-07-29 Yifan Wang , Runjin Chen , Bolian Li , David Cho , Yihe Deng , Ruqi Zhang , Tianlong Chen , Zhangyang Wang , Ananth Grama , Junyuan Hong

Aligning language models (LMs) with human preferences has become a key area of research, enabling these models to meet diverse user needs better. Inspired by weak-to-strong generalization, where a strong LM fine-tuned on labels generated by…

Computation and Language · Computer Science 2025-03-07 Wenhong Zhu , Zhiwei He , Xiaofeng Wang , Pengfei Liu , Rui Wang

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

Recent developments in Direct Preference Optimization (DPO) allow large language models (LLMs) to function as implicit ranking models by maximizing the margin between preferred and non-preferred responses. In practice, user feedback on such…

Machine Learning · Computer Science 2025-09-09 Junda Wu , Rohan Surana , Zhouhang Xie , Yiran Shen , Yu Xia , Tong Yu , Ryan A. Rossi , Prithviraj Ammanabrolu , Julian McAuley

Despite significant advancements in video large multimodal models (video-LMMs), achieving effective temporal grounding in long-form videos remains a challenge for existing models. To address this limitation, we propose Temporal Preference…

Computer Vision and Pattern Recognition · Computer Science 2025-09-03 Rui Li , Xiaohan Wang , Yuhui Zhang , Orr Zohar , Zeyu Wang , Serena Yeung-Levy

Domain adaptation faces a fundamental paradox in the cold-start regime. When target data is scarce, statistical methods fail to distinguish relevant source domains from irrelevant ones, which often leads to negative transfer. In this paper,…

Machine Learning · Computer Science 2026-05-15 Qiyuan Chen , Jiayu Zhou , Raed Al Kontar

Adapting large language models (LLMs) for specific tasks usually involves fine-tuning through reinforcement learning with human feedback (RLHF) on preference data. While these data often come from diverse labelers' groups (e.g., different…

Computation and Language · Computer Science 2024-05-31 Shyam Sundhar Ramesh , Yifan Hu , Iason Chaimalas , Viraj Mehta , Pier Giuseppe Sessa , Haitham Bou Ammar , Ilija Bogunovic

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

Effective social intelligence simulation requires language agents to dynamically adjust reasoning depth, a capability notably absent in current studies. Existing methods either lack explicit reasoning or employ lengthy Chain-of-Thought…

Computation and Language · Computer Science 2026-03-04 Minzheng Wang , Yongbin Li , Haobo Wang , Xinghua Zhang , Nan Xu , Bingli Wu , Fei Huang , Haiyang Yu , Wenji Mao

Conventional algorithms for training language models (LMs) with human feedback rely on preferences that are assumed to account for an "average" user, disregarding subjectivity and finer-grained variations. Recent studies have raised…

Computation and Language · Computer Science 2024-10-22 Sachin Kumar , Chan Young Park , Yulia Tsvetkov , Noah A. Smith , Hannaneh Hajishirzi

Preference optimization is a standard approach to fine-tuning large language models to align with human preferences. The quantity, diversity, and representativeness of the preference dataset are critical to the effectiveness of preference…

Computation and Language · Computer Science 2025-09-18 Yuu Jinnai , Ukyo Honda
‹ Prev 1 8 9 10 Next ›