English
Related papers

Related papers: From Noisy Traces to Stable Gradients: Bias-Varian…

200 papers

Although Large Language Models (LLMs) have made remarkable progress, current preference optimization methods still struggle to align directional consistency while preserving reasoning diversity. To address this limitation, we propose…

Computation and Language · Computer Science 2026-05-12 Mengyi Deng , Zhiwei Li , Xin Li , Tingyu Zhu , Yulan Yuan , Zhijiang Guo , Wei Wang

This paper presents Perceptual Preference Optimization (PerPO), a perception alignment method aimed at addressing the visual discrimination challenges in generative pre-trained multimodal large language models (MLLMs). To align MLLMs with…

Artificial Intelligence · Computer Science 2025-02-10 Zining Zhu , Liang Zhao , Kangheng Lin , Jinze Yang , En Yu , Chenglong Liu , Haoran Wei , Jianjian Sun , Zheng Ge , Xiangyu Zhang

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

Aligning large language models (LLMs) with human preferences is critical for real-world deployment, yet existing methods like RLHF face computational and stability challenges. While DPO establishes an offline paradigm with single…

Machine Learning · Computer Science 2025-10-28 Junkang Wu , Kexin Huang , Xue Wang , Jinyang Gao , Bolin Ding , Jiancan Wu , Xiangnan He , Xiang Wang

With the rapid advancement of large language models (LLMs), aligning policy models with human preferences has become increasingly critical. Direct Preference Optimization (DPO) has emerged as a promising approach for alignment, acting as an…

Artificial Intelligence · Computer Science 2025-07-15 Wenyi Xiao , Zechuan Wang , Leilei Gan , Shuai Zhao , Zongrui Li , Ruirui Lei , Wanggui He , Luu Anh Tuan , Long Chen , Hao Jiang , Zhou Zhao , Fei Wu

Recent breakthroughs in reasoning language models have significantly advanced text-based reasoning. On the other hand, Multi-modal Large Language Models (MLLMs) still lag behind, hindered by their outdated internal LLMs. Upgrading these…

Computer Vision and Pattern Recognition · Computer Science 2026-03-24 Yunhao Gou , Kai Chen , Zhili Liu , Lanqing Hong , Xin Jin , Zhenguo Li , James T. Kwok , Yu Zhang

In the realm of large language models (LLMs), the ability of models to accurately follow instructions is paramount as more agents and applications leverage LLMs for construction, where the complexity of instructions are rapidly increasing.…

Computation and Language · Computer Science 2025-07-18 Xinghua Zhang , Haiyang Yu , Cheng Fu , Fei Huang , Yongbin Li

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

Multimodal Large Reasoning Models introduce the reasoning paradigm, demonstrating strong capabilities on complex vision-language tasks. However, they still suffer from severe hallucinations. Existing training-based methods typically…

Artificial Intelligence · Computer Science 2026-05-28 Jiawei Kong , Hao Fang , Shunxiang Liao , Jinyu Li , Bin Chen , Hao Wu , Shu-Tao Xia , Min Zhang

Aligning large language models with human preferences is critical for creating reliable and controllable AI systems. A human preference can be visualized as a high-dimensional vector where different directions represent trade-offs between…

Computation and Language · Computer Science 2026-02-26 Ruochen Mao , Yuling Shi , Xiaodong Gu , Jiaheng Wei

Large language models (LLMs) used for multiple-choice and pairwise evaluation tasks often exhibit selection bias due to non-semantic factors like option positions and label symbols. Existing inference-time debiasing is costly and may harm…

Computation and Language · Computer Science 2026-05-01 Jinquan Zheng , Jia Yuan , Jiacheng Yao , Chenyang Gu , Pujun Zheng , Guoxiu He

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

Aligning large language models (LLMs) with human preferences is a critical challenge in AI research. While methods like Reinforcement Learning from Human Feedback (RLHF) and Direct Preference Optimization (DPO) are widely used, they often…

Computation and Language · Computer Science 2026-05-19 Xuan Qi , Rongwu Xu , Zhijing Jin

Aligning large language models (LLMs) with human values and intentions is crucial for their utility, honesty, and safety. Reinforcement learning from human feedback (RLHF) is a popular approach to achieve this alignment, but it faces…

Machine Learning · Computer Science 2025-07-22 Junkang Wu , Xue Wang , Zhengyi Yang , Jiancan Wu , Jinyang Gao , Bolin Ding , Xiang Wang , Xiangnan He

Aligning intelligent agents with human preferences and values is important. This paper examines two popular alignment methods: Direct Preference Optimization (DPO) and Reward-Model-Based Policy Optimization (RMB-PO). A variant of RMB-PO,…

Machine Learning · Computer Science 2024-02-27 Ziniu Li , Tian Xu , Yang Yu

Post-training of LLMs with RLHF, and subsequently preference optimization algorithms such as DPO, IPO, etc., made a big difference in improving human alignment. However, all such techniques can only work with a single (human) objective. In…

Machine Learning · Computer Science 2025-05-19 Akhil Agnihotri , Rahul Jain , Deepak Ramachandran , Zheng Wen

This study evaluates Direct Preference Optimization (DPO) and its variants for aligning Large Language Models (LLMs) with human preferences, testing three configurations: (1) with Supervised Fine Tuning (SFT), (2) without SFT, and (3)…

Computation and Language · Computer Science 2025-02-11 Amir Saeidi , Shivanshu Verma , Md Nayem Uddin , Chitta Baral

Fine-tuning Large Language Models (LLMs) with first-order methods like back-propagation is computationally intensive. Zeroth-Order (ZO) optimisation uses function evaluations instead of gradients, reducing memory usage, but suffers from…

Computation and Language · Computer Science 2025-07-24 Alessio Galatolo , Zhenbang Dai , Katie Winkle , Meriem Beloucif

Reinforcement Learning from Human Feedback (RLHF) has shown promise in aligning large language models (LLMs). Yet its reliance on a singular reward model often overlooks the diversity of human preferences. Recent approaches address this…

Computation and Language · Computer Science 2025-07-23 Tianze Wang , Dongnan Gui , Yifan Hu , Shuhang Lin , Linjun Zhang

Reinforcement Learning with Human Feedback (RLHF) has been the dominant approach for improving the reasoning capabilities of Large Language Models (LLMs). Recently, Reinforcement Learning with Verifiable Rewards (RLVR) has simplified this…

Computation and Language · Computer Science 2025-10-10 Yining Wang , Jinman Zhao , Chuangxin Zhao , Shuhao Guan , Gerald Penn , Shinan Liu