English
Related papers

Related papers: Thinking Preference Optimization

200 papers

Direct Preference Optimization (DPO) has recently emerged as a popular approach to improve reinforcement learning with human feedback (RLHF), leading to better techniques to fine-tune large language models (LLM). A weakness of DPO, however,…

Machine Learning · Computer Science 2025-04-21 Haoxian Chen , Hanyang Zhao , Henry Lam , David Yao , Wenpin Tang

As the era of large language models (LLMs) unfolds, Preference Optimization (PO) methods have become a central approach to aligning LLMs with human preferences and improving performance. We propose Maximum a Posteriori Preference…

Preference optimization has become an important post-training paradigm for improving the reasoning abilities of large language models. Existing methods typically rely on externally constructed preference data, using preferred and…

Computation and Language · Computer Science 2026-05-13 Yifan Le

Human preference alignment is critical in building powerful and reliable large language models (LLMs). However, current methods either ignore the multi-dimensionality of human preferences (e.g. helpfulness and harmlessness) or struggle with…

Machine Learning · Computer Science 2024-10-14 Xingzhou Lou , Junge Zhang , Jian Xie , Lifeng Liu , Dong Yan , Kaiqi Huang

Large Language Models (LLMs) have shown impressive reasoning capabilities in well-defined problems with clear solutions, such as mathematics and coding. However, they still struggle with complex real-world scenarios like business…

Computation and Language · Computer Science 2025-05-29 Xiaoqian Liu , Ke Wang , Yongbin Li , Yuchuan Wu , Wentao Ma , Aobo Kong , Fei Huang , Jianbin Jiao , Junge Zhang

Small Vision Language Models (SVLMs) generally refer to models with parameter sizes less than or equal to 2B. Their low cost and power consumption characteristics confer high commercial value. However, their reasoning abilities are limited…

Computer Vision and Pattern Recognition · Computer Science 2025-08-12 Fanyi Wang , Binzhi Dong , Haotian Hu , Jinjin Xu , Zhiwang Zhang

Large reasoning models (LRMs) have exhibited remarkable reasoning capabilities through inference-time scaling, but this progress has also introduced considerable redundancy and inefficiency into their reasoning processes, resulting in…

Artificial Intelligence · Computer Science 2025-07-18 Xingyang He , Xiao Ling , Jie Liu

While recent success of large reasoning models (LRMs) significantly advanced LLMs' reasoning capability by optimizing the final answer accuracy using reinforcement learning, they may also drastically increase the output length due to…

Artificial Intelligence · Computer Science 2025-05-29 Sohyun An , Ruochen Wang , Tianyi Zhou , Cho-Jui Hsieh

Reasoning is a cognitive process of using evidence to reach a sound conclusion. The reasoning capability is essential for large language models (LLMs) to serve as the brain of the artificial general intelligence agent. Recent studies reveal…

Computation and Language · Computer Science 2023-09-06 Peiyi Wang , Lei Li , Liang Chen , Feifan Song , Binghuai Lin , Yunbo Cao , Tianyu Liu , Zhifang Sui

Fine-tuning is integral for aligning large language models (LLMs) with human preferences. Multiple-Reference Preference Optimization (MRPO) builds on Direct Preference Optimization (DPO) by fine-tuning LLMs on preference datasets while…

Machine Learning · Computer Science 2025-12-12 Skyler Wu , Aymen Echarghaoui

As Test-Time Scaling emerges as an active research focus in the large language model community, advanced post-training methods increasingly emphasize extending chain-of-thought (CoT) generation length, thereby enhancing reasoning…

Artificial Intelligence · Computer Science 2025-05-20 Muzhi Dai , Chenxu Yang , Qingyi Si

Test-time compute scaling has demonstrated the ability to improve the performance of reasoning language models by generating longer chain-of-thought (CoT) sequences. However, this increase in performance comes with a significant increase in…

Artificial Intelligence · Computer Science 2025-09-24 Adarsha Balaji , Le Chen , Rajeev Thakur , Franck Cappello , Sandeep Madireddy

Supervised fine-tuning (SFT) of foundation models often leads to poor generalization, where prior capabilities deteriorate after tuning on new tasks or domains. Inspired by trust-region policy optimization (TRPO) and proximal policy…

Machine Learning · Computer Science 2026-04-14 Wenhong Zhu , Ruobing Xie , Rui Wang , Xingwu Sun , Di Wang , Pengfei Liu

Software engineering presents complex, multi-step challenges for Large Language Models (LLMs), requiring reasoning over large codebases and coordinated tool use. The difficulty of these tasks is exemplified by benchmarks like SWE-bench,…

Artificial Intelligence · Computer Science 2026-02-05 Jiahao Yu , Zelei Cheng , Xian Wu , Xinyu Xing

The post-training of LLMs, which typically consists of the supervised fine-tuning (SFT) stage and the preference learning stage (RLHF or DPO), is crucial to effective and safe LLM applications. The widely adopted approach in post-training…

Machine Learning · Computer Science 2025-11-11 Heshan Fernando , Han Shen , Parikshit Ram , Yi Zhou , Horst Samulowitz , Nathalie Baracaldo , Tianyi Chen

Self-alignment, whereby models learn to improve themselves without human annotation, is a rapidly growing research area. However, existing techniques often fail to improve complex reasoning tasks due to the difficulty of assigning correct…

Computation and Language · Computer Science 2025-07-08 Archiki Prasad , Weizhe Yuan , Richard Yuanzhe Pang , Jing Xu , Maryam Fazel-Zarandi , Mohit Bansal , Sainbayar Sukhbaatar , Jason Weston , Jane Yu

Program-of-Thought (PoT), which aims to use programming language instead of natural language as an intermediate step in reasoning, is an important way for LLMs to solve mathematical problems. Since different programming languages excel in…

Computation and Language · Computer Science 2024-12-18 Nianqi Li , Zujie Liang , Siyu Yuan , Jiaqing Liang , Feng Wei , Yanghua Xiao

General-purpose Large Language Models (LLMs) are frequently fine-tuned through supervised fine-tuning (SFT) to enhance performance in specific domains. Better results can be achieved by distilling the chain-of-thought of a larger model at…

Machine Learning · Computer Science 2026-03-24 Andrey Goncharov , Daniil Vyazhev , Petr Sychev , Edvard Khalafyan , Alexey Zaytsev

Reinforcement Learning (RL) has proven to be an effective post-training strategy for enhancing reasoning in vision-language models (VLMs). Group Relative Policy Optimization (GRPO) is a recent prominent method that encourages models to…

Artificial Intelligence · Computer Science 2025-10-30 Jiaqi Wang , Kevin Qinghong Lin , James Cheng , Mike Zheng Shou

DeepSeek R1 has significantly advanced complex reasoning for large language models (LLMs). While recent methods have attempted to replicate R1's reasoning capabilities in multimodal settings, they face limitations, including inconsistencies…

Computer Vision and Pattern Recognition · Computer Science 2025-05-28 Zhehan Kan , Yanlin Liu , Kun Yin , Xinghua Jiang , Xin Li , Haoyu Cao , Yinsong Liu , Deqiang Jiang , Xing Sun , Qingmin Liao , Wenming Yang