English
Related papers

Related papers: Thinking Preference Optimization

200 papers

Using effective generalization capabilities of vision language models (VLMs) in context-specific dynamic tasks for embodied artificial intelligence remains a significant challenge. Although supervised fine-tuned models can better align with…

Artificial Intelligence · Computer Science 2025-09-11 Kechen Jiao , Zhirui Fang , Jiahao Liu , Bei Li , Qifan Wang , Xinyu Liu , Junhao Ruan , Zhongjian Qiao , Yifan Zhu , Yaxin Xu , Jingang Wang , Xiu Li

Large reasoning models (LRMs) are commonly trained with reinforcement learning (RL) to explore long chain-of-thought reasoning, achieving strong performance at high computational cost. Recent methods add multi-reward objectives to jointly…

Artificial Intelligence · Computer Science 2026-02-17 Anhao Zhao , Ziyang Chen , Junlong Tong , Yingqi Fan , Fanghua Ye , Shuhao Li , Yunpu Ma , Wenjie Li , Xiaoyu Shen

Large Language Models (LLMs) increasingly rely on Chain-of-Thought (CoT) reasoning to improve accuracy on complex tasks. However, always generating lengthy reasoning traces is inefficient, leading to excessive token usage and higher…

Direct Preference Optimization (DPO) has proven effective in complex reasoning tasks like math word problems and code generation. However, when applied to Text-to-SQL datasets, it often fails to improve performance and can even degrade it.…

Computation and Language · Computer Science 2025-02-18 Hanbing Liu , Haoyang Li , Xiaokang Zhang , Ruotong Chen , Haiyong Xu , Tian Tian , Qi Qi , Jing Zhang

A practical approach to activate long chain-of-thoughts reasoning ability in pre-trained large language models is to perform supervised fine-tuning on instruction datasets synthesized by strong Large Reasoning Models such as DeepSeek-R1,…

Computation and Language · Computer Science 2025-12-24 Cehao Yang , Xueyuan Lin , Xiaojun Wu , Chengjin Xu , Xuhui Jiang , Honghao Liu , Hui Xiong , Jian Guo

Recent advancements in Large Language Models (LLMs) have shifted from explicit Chain-of-Thought (CoT) reasoning to more efficient latent reasoning, where intermediate thoughts are represented as vectors rather than text. However, latent…

Computation and Language · Computer Science 2026-01-27 Wengao Ye , Yan Liang , Lianlei Shan

Supervised fine-tuning (SFT) on chain-of-thought data is an essential post-training step for reasoning language models. Standard machine learning intuition suggests that training with more unique training samples yields better…

Computation and Language · Computer Science 2026-02-12 Dawid J. Kopiczko , Sagar Vaze , Tijmen Blankevoort , Yuki M. Asano

Preference optimization techniques, such as Direct Preference Optimization (DPO), are frequently employed to enhance the reasoning capabilities of large language models (LLMs) in domains like mathematical reasoning and coding, typically…

Computation and Language · Computer Science 2025-02-17 Fangkai Jiao , Geyang Guo , Xingxing Zhang , Nancy F. Chen , Shafiq Joty , Furu Wei

Iterative preference optimization methods have recently been shown to perform well for general instruction tuning tasks, but typically make little improvement on reasoning tasks (Yuan et al., 2024, Chen et al., 2024). In this work we…

Computation and Language · Computer Science 2024-06-27 Richard Yuanzhe Pang , Weizhe Yuan , Kyunghyun Cho , He He , Sainbayar Sukhbaatar , Jason Weston

Supervised and preference-based fine-tuning techniques have become popular for aligning large language models (LLMs) with user intent and correctness criteria. However, real-world training data often exhibits spurious correlations --…

Computation and Language · Computer Science 2025-05-12 Julia Shuieh , Prasann Singhal , Apaar Shanker , John Heyer , George Pu , Samuel Denton

Post-training processes are essential phases in grounding pre-trained language models to real-world tasks, with learning from demonstrations or preference signals playing a crucial role in this adaptation. We present a unified theoretical…

Machine Learning · Computer Science 2025-07-08 Bo Wang , Qinyuan Cheng , Runyu Peng , Rong Bao , Peiji Li , Qipeng Guo , Linyang Li , Zhiyuan Zeng , Yunhua Zhou , Xipeng Qiu

Existing work has shown that o1-level performance can be achieved with limited data distillation, but most existing methods focus on unidirectional supervised fine-tuning (SFT), overlooking the intricate interplay between diverse reasoning…

Machine Learning · Computer Science 2025-09-17 Mengyi Deng , Xin Li , Tingyu Zhu , Zhicheng Yang , Zhijiang Guo , Wei Wang

Inference-time scaling enhances the reasoning ability of a language model (LM) by extending its chain-of-thought (CoT). However, existing approaches typically generate the entire reasoning chain in a single forward pass, which often leads…

Computation and Language · Computer Science 2025-10-20 Siheng Xiong , Ali Payani , Faramarz Fekri

Direct Preference Optimization (DPO) has proven effective at improving the performance of large language models (LLMs) on downstream tasks such as reasoning and alignment. In this work, we propose Step-Controlled DPO (SCDPO), a method for…

Computation and Language · Computer Science 2024-07-16 Zimu Lu , Aojun Zhou , Ke Wang , Houxing Ren , Weikang Shi , Junting Pan , Mingjie Zhan , Hongsheng Li

While Reinforcement Learning with Verifiable Rewards has enhanced the reasoning of large-scale language models (LLMs), its efficacy for lightweight multimodal language models (MLLMs) with fewer than seven billion parameters remains…

Computer Vision and Pattern Recognition · Computer Science 2025-10-10 Linyu Ou , YuYang Yin

Large language models (LLMs) struggle with complex, long-horizon reasoning due to instability caused by their frozen policy assumption. Current test-time scaling methods treat execution feedback merely as an external signal for filtering or…

Artificial Intelligence · Computer Science 2026-01-29 Zhengbo Jiao , Hongyu Xian , Qinglong Wang , Yunpu Ma , Zhebo Wang , Zifan Zhang , Dezhang Kong , Meng Han

Direct Preference Optimization (DPO) is widely used after supervised fine-tuning (SFT) to align language models, yet empirical behavior under small backbones and modest data is under-specified. We systematically compare SFT-only, DPO-only,…

Computation and Language · Computer Science 2026-03-23 Yuming Feng , Christy Yang

Direct Preference Optimization (DPO) is an effective framework for aligning large language models with human preferences, but it struggles with complex reasoning tasks. DPO optimizes for the likelihood of generating preferred over…

Artificial Intelligence · Computer Science 2026-04-23 Darsh Kachroo , Adriana Caraeni , Arjun Prasaath Anbazhagan , Brennan Lagasse , Kevin Zhu

Mathematical reasoning presents a significant challenge for Large Language Models (LLMs) as it requires ensuring the correctness of each reasoning step. Researchers have been strengthening the mathematical reasoning abilities of LLMs…

Machine Learning · Computer Science 2025-06-23 Yunze Lin

Applying Reinforcement Learning (RL) to Video Large Language Models (Video-LLMs) shows significant promise for complex video reasoning. However, popular Reinforcement Fine-Tuning (RFT) methods, such as outcome-based Group Relative Policy…

Computation and Language · Computer Science 2025-05-27 Yunxin Li , Xinyu Chen , Zitao Li , Zhenyu Liu , Longyue Wang , Wenhan Luo , Baotian Hu , Min Zhang