English
Related papers

Related papers: Stepwise Think-Critique: A Unified Framework for R…

200 papers

Large Language Models have achieved strong performance on reasoning tasks with objective answers by generating step-by-step solutions, but diagnosing where a multi-step reasoning trace might fail remains difficult. Confidence estimation…

Computation and Language · Computer Science 2026-05-20 Xiaoou Liu , Tiejin Chen , Dengjia Zhang , Yaqing Wang , Lu Cheng , Hua Wei

Through reinforcement learning with verifiable rewards (RLVR), large language models have achieved substantial progress in domains with easily verifiable outcomes, such as mathematics and coding. However, when applied to more complex tasks…

Computation and Language · Computer Science 2025-10-01 Qiyao Ma , Yunsheng Shi , Hongtao Tian , Chao Wang , Weiming Chang , Ting Yao

Large language models (LLMs) have been routinely used to solve various tasks using step-by-step reasoning. However, the structure of intermediate reasoning steps, or thoughts, is rigid and unidirectional, such as chains, trees, or…

Artificial Intelligence · Computer Science 2024-12-30 Sijia Chen , Baochun Li

Current LLM post-training methods optimize complete reasoning trajectories through Supervised Fine-Tuning (SFT) followed by outcome-based Reinforcement Learning (RL). While effective, a closer examination reveals a fundamental gap: this…

Artificial Intelligence · Computer Science 2026-05-29 Shaojie Wang , Liang Zhang

Large language models (LLMs) are typically trained by reinforcement learning (RL) with verifiable rewards (RLVR) and supervised fine-tuning (SFT) on reasoning traces to improve their reasoning abilities. However, how these methods shape…

Artificial Intelligence · Computer Science 2026-05-28 Kohsei Matsutani , Shota Takashiro , Gouki Minegishi , Takeshi Kojima , Yusuke Iwasawa , Yutaka Matsuo

The ability of Large Language Models (LLMs) to critique and refine their reasoning is crucial for their application in evaluation, feedback provision, and self-improvement. This paper introduces CriticBench, a comprehensive benchmark…

Computation and Language · Computer Science 2024-06-04 Zicheng Lin , Zhibin Gou , Tian Liang , Ruilin Luo , Haowei Liu , Yujiu Yang

Enhancing the reasoning capabilities of large language models (LLMs), particularly for complex tasks requiring multi-step logical deductions, remains a significant challenge. Traditional inference time scaling methods utilize scalar reward…

Computation and Language · Computer Science 2025-03-24 Yansi Li , Jiahao Xu , Tian Liang , Xingyu Chen , Zhiwei He , Qiuzhi Liu , Rui Wang , Zhuosheng Zhang , Zhaopeng Tu , Haitao Mi , Dong Yu

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 large language models (LLMs) have demonstrated remarkable reasoning capabilities, they often struggle with complex tasks that require specific thinking paradigms, such as divide-and-conquer and procedural deduction, \etc Previous…

Software Engineering · Computer Science 2025-06-05 Kechi Zhang , Ge Li , Jia Li , Huangzhao Zhang , Jingjing Xu , Hao Zhu , Lecheng Wang , Jia Li , Yihong Dong , Jing Mai , Bin Gu , Zhi Jin

Large language models (LLMs) primarily rely on supervised fine-tuning (SFT) as a key method to adapt pre-trained models to domain-specific tasks such as mathematical reasoning. However, standard SFT uniformly penalizes all tokens,…

Computation and Language · Computer Science 2025-10-14 Zhiwen Ruan , Yixia Li , He Zhu , Yun Chen , Peng Li , Yang Liu , Guanhua Chen

Human cognition naturally engages with abstract and fluid concepts, whereas existing reasoning models often rely on generating discrete tokens, potentially constraining their expressive capabilities. Recent advancements aim to address this…

Computation and Language · Computer Science 2025-10-17 Junhong Wu , Jinliang Lu , Zixuan Ren , Gangqiang Hu , Zhi Wu , Dai Dai , Hua Wu

Self-correction in language models remains elusive. In this work, we explore whether language models can explicitly localize errors in incorrect reasoning, as a path toward building AI systems that can effectively correct themselves. We…

Large Language Models (LLMs) increasingly rely on long-form, multi-step reasoning to solve complex tasks such as mathematical problem solving and scientific question answering. Despite strong performance, existing confidence estimation…

Computation and Language · Computer Science 2026-01-21 Zhenjiang Mao , Anirudhh Venkat , Artem Bisliouk , Akshat Kothiyal , Sindhura Kumbakonam Subramanian , Saithej Singhu , Ivan Ruchkin

Chain-based reasoning methods like chain of thought (CoT) play a rising role in solving reasoning tasks for large language models (LLMs). However, the causal hallucinations between a step of reasoning and corresponding state transitions are…

Computation and Language · Computer Science 2025-03-25 Kangsheng Wang , Xiao Zhang , Juntao Lyu , Tianyu Hu , Huimin Ma

In recent years, large language models (LLMs) have demonstrated significant potential in complex reasoning tasks like mathematical problem-solving. However, existing research predominantly relies on reinforcement learning (RL) frameworks…

Machine Learning · Computer Science 2026-01-12 ShaoZhen Liu , Xinting Huang , Houwen Peng , Xin Chen , Xinyang Song , Qi Li , Zhenan Sun

Automatic grading of subjective questions remains a significant challenge in examination assessment due to the diversity in question formats and the open-ended nature of student responses. Existing works primarily focus on a specific type…

Computation and Language · Computer Science 2025-10-10 Fanwei Zhua , Jiaxuan He , Xiaoxiao Chen , Zulong Chen , Quan Lu , Chenrui Mei

State-of-the-art large language models (LLMs) exhibit impressive problem-solving capabilities but may struggle with complex reasoning and factual correctness. Existing methods harness the strengths of chain-of-thought and…

Computation and Language · Computer Science 2024-10-03 Xingxuan Li , Weiwen Xu , Ruochen Zhao , Fangkai Jiao , Shafiq Joty , Lidong Bing

Large language models (LLMs) can improve their accuracy on various tasks through iteratively refining and revising their output based on feedback. We observe that these revisions can introduce errors, in which case it is better to roll back…

Artificial Intelligence · Computer Science 2023-09-26 Kumar Shridhar , Harsh Jhamtani , Hao Fang , Benjamin Van Durme , Jason Eisner , Patrick Xia

The recent progress in large language models (LLMs), especially the invention of chain-of-thought prompting, has made it possible to automatically answer questions by stepwise reasoning. However, when faced with more complicated problems…

Artificial Intelligence · Computer Science 2023-10-06 Ning Miao , Yee Whye Teh , Tom Rainforth

Large Language Models (LLMs) are typically trained to reflect a relatively uniform set of values, which limits their applicability to tasks that require understanding of nuanced human perspectives. Recent research has underscored the…

Computation and Language · Computer Science 2025-10-07 Yunfan Zhang , Kathleen McKeown , Smaranda Muresan