中文
相关论文

相关论文: Let's reward step by step: Step-Level reward model…

200 篇论文

Process Reward Models (PRMs) have emerged as a powerful tool for providing step-level feedback when evaluating the reasoning of Large Language Models (LLMs), which frequently produce chains of thought (CoTs) containing errors even when the…

计算与语言 · 计算机科学 2026-04-21 Raffaele Pisano , Roberto Navigli

Large Language Models (LLMs) are prone to hallucination, especially during multi-hop and reasoning-intensive tasks such as mathematical problem solving. While Outcome Reward Models verify only final answers, Process Reward Models (PRMs)…

计算与语言 · 计算机科学 2025-05-27 Tej Deep Pala , Panshul Sharma , Amir Zadeh , Chuan Li , Soujanya Poria

Large language models (LLMs) inevitably make mistakes when performing step-by-step mathematical reasoning. Process Reward Models (PRMs) have emerged as a promising solution by evaluating each reasoning step. However, existing PRMs typically…

计算与语言 · 计算机科学 2025-03-28 Shuaijie She , Junxiao Liu , Yifeng Liu , Jiajun Chen , Xin Huang , Shujian Huang

A promising approach for improving reasoning in large language models is to use process reward models (PRMs). PRMs provide feedback at each step of a multi-step reasoning trace, potentially improving credit assignment over outcome reward…

Recent progress in large language models (LLM) found chain-of-thought prompting strategies to improve the reasoning ability of LLMs by encouraging problem solving through multiple steps. Therefore, subsequent research aimed to integrate the…

计算与语言 · 计算机科学 2025-02-21 Ting-Ruen Wei , Haowei Liu , Xuyang Wu , Yi Fang

Large reasoning models (LRMs) have recently shown promise in solving complex math problems when optimized with Reinforcement Learning (RL). But conventional approaches rely on outcome-only rewards that provide sparse feedback, resulting in…

机器学习 · 计算机科学 2025-08-01 Tao He , Rongchuan Mu , Lizi Liao , Yixin Cao , Ming Liu , Bing Qin

Recent studies show that Large Language Models (LLMs) achieve strong reasoning capabilities through supervised fine-tuning or reinforcement learning. However, a key approach, the Process Reward Model (PRM), suffers from reward hacking,…

While Multimodal Large Language Models (MLLMs) have achieved impressive progress in vision-language understanding, they still struggle with complex multi-step reasoning, often producing logically inconsistent or partially correct solutions.…

人工智能 · 计算机科学 2025-06-06 Lingxiao Du , Fanqing Meng , Zongkai Liu , Zhixiang Zhou , Ping Luo , Qiaosheng Zhang , Wenqi Shao

Large language models (LLMs) have exhibited extraordinary performance in a variety of tasks while it remains challenging for them to solve complex multi-step tasks as agents. In practice, agents sensitive to the outcome of certain key steps…

Large Language Models (LLMs) are increasingly relied upon for solving complex reasoning tasks in domains such as mathematics, logic, and multi-step question answering. A growing line of work seeks to improve reasoning quality by scaling…

机器学习 · 计算机科学 2025-08-05 Seyyed Saeid Cheshmi , Azal Ahmad Khan , Xinran Wang , Zirui Liu , Ali Anwar

Process Reward Models (PRMs) have emerged as a promising approach to enhance the reasoning capabilities of large language models (LLMs) by guiding their step-by-step reasoning toward a final answer. However, existing PRMs either treat each…

机器学习 · 计算机科学 2026-03-02 Zheng Zhang , Ziwei Shan , Kaitao Song , Yexin Li , Kan Ren

Large Language Models have demonstrated outstanding performance across various downstream tasks and have been widely applied in multiple scenarios. Human-annotated preference data is used for training to further improve LLMs' performance,…

计算与语言 · 计算机科学 2025-03-06 Shimao Zhang , Xiao Liu , Xin Zhang , Junxiao Liu , Zheheng Luo , Shujian Huang , Yeyun Gong

Improving the multi-step reasoning ability of Large Language Models (LLMs) is a critical yet challenging task. The dominant paradigm, outcome-supervised reinforcement learning (RLVR), rewards only correct final answers, often propagating…

人工智能 · 计算机科学 2025-10-14 Beining Wang , Weihang Su , Hongtao Tian , Tao Yang , Yujia Zhou , Ting Yao , Qingyao Ai , Yiqun Liu

Multimodal Large Language Models (MLLMs) demonstrate remarkable capabilities but often struggle with complex, multi-step mathematical reasoning, where minor errors in visual perception or logical deduction can lead to complete failure.…

计算与语言 · 计算机科学 2025-08-08 Jianghangfan Zhang , Yibo Yan , Kening Zheng , Xin Zou , Song Dai , Xuming Hu

Process Reward Models (PRMs) aim to improve multi-step reasoning in Large Language Models (LLMs) by supervising intermediate steps and identifying errors. However, building effective PRMs remains challenging due to the lack of scalable,…

人工智能 · 计算机科学 2025-10-17 Yao Zhang , Yu Wu , Haowei Zhang , Weiguo Li , Haokun Chen , Jingpei Wu , Guohao Li , Zhen Han , Volker Tresp

Large language models (LLMs) are designed to perform a wide range of tasks. To improve their ability to solve complex problems requiring multi-step reasoning, recent research leverages process reward modeling to provide fine-grained…

计算与语言 · 计算机科学 2025-09-29 Weixuan Wang , Minghao Wu , Barry Haddow , Alexandra Birch

Despite significant advancements in Large Language Models (LLMs), developing advanced reasoning capabilities in LLMs remains a key challenge. Process Reward Models (PRMs) have demonstrated exceptional promise in enhancing reasoning by…

计算与语言 · 计算机科学 2025-06-26 Miao Peng , Nuo Chen , Zongrui Suo , Jia Li

Although Large Language Models (LLMs) exhibit advanced reasoning ability, conventional alignment remains largely dominated by outcome reward models (ORMs) that judge only final answers. Process Reward Models(PRMs) address this gap by…

Multi-step reasoning improves the capabilities of large language models (LLMs) but increases the risk of errors propagating through intermediate steps. Process reward models (PRMs) mitigate this by scoring each step individually, enabling…

计算与语言 · 计算机科学 2026-03-19 Corentin Royer , Debarun Bhattacharjya , Gaetano Rossiello , Andrea Giovannini , Mennatallah El-Assady

Step-level reward models (SRMs) can significantly enhance mathematical reasoning performance through process supervision or step-level preference alignment based on reinforcement learning. The performance of SRMs is pivotal, as they serve…

人工智能 · 计算机科学 2025-03-11 Yiran Ma , Zui Chen , Tianqiao Liu , Mi Tian , Zhuo Liu , Zitao Liu , Weiqi Luo
‹ 上一页 1 2 3 10 下一页 ›