English
Related papers

Related papers: LongDPO: Unlock Better Long-form Generation Abilit…

200 papers

Mathematical reasoning presents a significant challenge for Large Language Models (LLMs) due to the extensive and precise chain of reasoning required for accuracy. Ensuring the correctness of each reasoning step is critical. To address…

Machine Learning · Computer Science 2024-06-28 Xin Lai , Zhuotao Tian , Yukang Chen , Senqiao Yang , Xiangru Peng , Jiaya Jia

We introduce an approach aimed at enhancing the reasoning capabilities of Large Language Models (LLMs) through an iterative preference learning process inspired by the successful strategy employed by AlphaZero. Our work leverages Monte…

Artificial Intelligence · Computer Science 2024-06-19 Yuxi Xie , Anirudh Goyal , Wenyue Zheng , Min-Yen Kan , Timothy P. Lillicrap , Kenji Kawaguchi , Michael Shieh

Direct Preference Optimization (DPO) and its variants have become the de facto standards for aligning large language models (LLMs) with human preferences or specific goals. However, DPO requires high-quality preference data and suffers from…

Machine Learning · Computer Science 2024-11-12 Zhuotong Chen , Fang Liu , Jennifer Zhu , Wanyu Du , Yanjun Qi

In the domain of complex reasoning tasks, such as mathematical reasoning, recent advancements have proposed the use of Direct Preference Optimization (DPO) to suppress output of dispreferred responses, thereby enhancing the long-chain…

Computation and Language · Computer Science 2025-10-27 Weibin Liao , Xu Chu , Yasha Wang

As creative writing tasks do not have singular correct answers, large language models (LLMs) trained to perform these tasks should be able to generate diverse valid outputs. However, LLM post-training often focuses on improving generation…

Computation and Language · Computer Science 2025-03-24 John Joon Young Chung , Vishakh Padmakumar , Melissa Roemmele , Yuqian Sun , Max Kreminski

Direct Preference Optimization (DPO) has emerged as a de-facto approach for aligning language models with human preferences. Recent work has shown DPO's effectiveness relies on training data quality. In particular, clear quality differences…

Machine Learning · Computer Science 2025-01-28 Nirav Diwan , Tolga Ergen , Dongsub Shim , Honglak Lee

Direct Preference Optimization (DPO) using an implicit reward model has proven to be an effective alternative to reinforcement learning from human feedback (RLHF) for fine-tuning preference aligned large language models (LLMs). However, the…

Computation and Language · Computer Science 2024-09-30 Guoxin Chen , Minpeng Liao , Chengxi Li , Kai Fan

As development of large language models (LLM) progresses, aligning them with human preferences has become increasingly important. We propose stepwise DPO (sDPO), an extension of the recently popularized direct preference optimization (DPO)…

Computation and Language · Computer Science 2024-10-08 Dahyun Kim , Yungi Kim , Wonho Song , Hyeonwoo Kim , Yunsu Kim , Sanghoon Kim , Chanjun Park

The code generation capabilities of Large Language Models (LLMs) have advanced applications like tool invocation and problem-solving. However, improving performance in code-related tasks remains challenging due to limited training data that…

Computation and Language · Computer Science 2025-08-28 Houxing Ren , Zimu Lu , Weikang Shi , Haotian Hou , Yunqiao Yang , Ke Wang , Aojun Zhou , Junting Pan , Mingjie Zhan , Hongsheng Li

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

Recent advances in Large Reasoning Models (LRMs) have demonstrated strong performance on complex tasks through long Chain-of-Thought (CoT) reasoning. However, their lengthy outputs increase computational costs and may lead to overthinking,…

Artificial Intelligence · Computer Science 2026-04-16 Bin Hong , Jiayu Liu , Kai Zhang , Jianwen Sun , Mengdi Zhang , Zhenya Huang

Large language models (LLMs) have demonstrated their remarkable capacity across a variety of tasks. However, reasoning remains a challenge for LLMs. To improve LLMs' reasoning ability, process supervision has proven to be better than…

Artificial Intelligence · Computer Science 2025-01-06 Shuangtao Li , Shuaihao Dong , Kexin Luan , Xinhan Di , Chaofan Ding

Recently, preference optimization methods such as DPO have significantly enhanced large language models (LLMs) in wide tasks including dialogue and question-answering. However, current methods fail to account for the varying difficulty…

Computation and Language · Computer Science 2024-12-31 Jingyuan Ma , Rui Li , Zheng Li , Lei Sha , Zhifang Sui

Direct Preference Optimization (DPO) has been proposed as an effective and efficient alternative to reinforcement learning from human feedback (RLHF). In this paper, we propose a novel and enhanced version of DPO based on curriculum…

Computer Vision and Pattern Recognition · Computer Science 2025-05-12 Florinel-Alin Croitoru , Vlad Hondru , Radu Tudor Ionescu , Nicu Sebe , Mubarak Shah

Large language models (LLMs) have shown remarkable performance across various tasks, yet their ability to handle long-context reading remains challenging. This study explores the effectiveness of leveraging high-quality academic peer review…

Computation and Language · Computer Science 2024-11-11 Shengzhi Li , Kittipat Kampa , Rongyu Lin , Bohang Li , Shichao Pei

Code generation models have shown significant potential for programming tasks. However, existing training methods like supervised fine-tuning face key limitations: they do not effectively teach models to prioritize correct over incorrect…

Software Engineering · Computer Science 2025-06-04 Kechi Zhang , Ge Li , Yihong Dong , Jingjing Xu , Jun Zhang , Jing Su , Yongfei Liu , Zhi Jin

Post-training of language models, either through reinforcement learning, preference optimization or supervised finetuning, tends to sharpen the output probability distribution and reduce the diversity of generated responses. This is…

Computation and Language · Computer Science 2025-05-23 Jack Lanchantin , Angelica Chen , Shehzaad Dhuliawala , Ping Yu , Jason Weston , Sainbayar Sukhbaatar , Ilia Kulikov

Mathematical reasoning is a crucial capability for Large Language Models (LLMs), yet generating detailed and accurate reasoning traces remains a significant challenge. This paper introduces a novel approach to produce high-quality reasoning…

Computation and Language · Computer Science 2024-10-30 Yihe Deng , Paul Mineiro

Aligning Large Language Models (LLMs) with human feedback is crucial for their development. Existing preference optimization methods such as DPO and KTO, while improved based on Reinforcement Learning from Human Feedback (RLHF), are…

Computation and Language · Computer Science 2024-12-23 Shuo Xie , Fangzhi Zhu , Jiahui Wang , Lulu Wen , Wei Dai , Xiaowei Chen , Junxiong Zhu , Kai Zhou , Bo Zheng

Long-form text generation remains a significant challenge for large language models (LLMs), particularly in maintaining coherence, ensuring logical consistency, and preserving text quality as sequence length increases. To address these…

Computation and Language · Computer Science 2025-06-05 Yuhao Wu , Yushi Bai , Zhiqiang Hu , Juanzi Li , Roy Ka-Wei Lee
‹ Prev 1 2 3 10 Next ›