Breaking down a problem into intermediate steps has demonstrated impressive performance in Large Language Model (LLM) reasoning. However, the growth of the reasoning chain introduces uncertainty and error accumulation, making it challenging to elicit accurate final results. To tackle this challenge of uncertainty in multi-step reasoning, we introduce a stepwise self-evaluation mechanism to guide and calibrate the reasoning process of LLMs. We propose a decoding algorithm integrating the self-evaluation guidance via stochastic beam search. The self-evaluation guidance serves as a better-calibrated automatic criterion, facilitating an efficient search in the reasoning space and resulting in superior prediction quality. Stochastic beam search balances exploitation and exploration of the search space with temperature-controlled randomness. Our approach surpasses the corresponding Codex-backboned baselines in few-shot accuracy by $6.34\%$, $9.56\%$, and $5.46\%$ on the GSM8K, AQuA, and StrategyQA benchmarks, respectively. Experiment results with Llama-2 on arithmetic reasoning demonstrate the efficiency of our method in outperforming the baseline methods with comparable computational budgets. Further analysis in multi-step reasoning finds our self-evaluation guidance pinpoints logic failures and leads to higher consistency and robustness. Our code is publicly available at https://guideddecoding.github.io/.
BeamPERL: Parameter-Efficient RL with Verifiable Rewards Specializes Compact LLMs for Structured Beam Mechanics Reasoning
Department of Mechanical Engineering(机械工程系);Massachusetts Institute of Technology(麻省理工学院);Department of Civil and Environmental Engineering(土木与环境工程系);Schwarzman College of Computing(施瓦茨曼计算学院)
Beyond representational alignment with brain-guided language models for robust reasoning
State Key Lab of General AI, School of Intelligence Science and Technology, Peking University(北京大学通用人工智能国家重点实验室、智能科学与技术学院);Department of Psychological and Cognitive Sciences, Tsinghua University(清华大学心理与认知科学系);Microsoft Research Asia(微软亚洲研究院)
GAMR: A Guided Attention Model for (visual) Reasoning
Carney Institute for Brain Science(卡尼脑科学研究所);Brown University(布朗大学);Centre de Recherche Cerveau et Cognition(脑与认知研究中心);CNRS(法国国家科学研究中心);Université de Toulouse(图卢兹大学);Artificial and Natural Intelligence Toulouse Institute(图卢兹人工智能与自然智能研究所)
KREL: Automatic Medical Coding via Knowledge-Guided Reasoning over Clinical Evidence with LLMs
The University of New South Wales(新南威尔士大学);University of Göttingen(哥廷根大学);Macquarie University(麦考瑞大学);Beijing Intelligent Decision Medical Technology Co. Ltd(北京智决医疗科技有限公司)
Expert-Guided LLM Reasoning for Battery Discovery: From AI-Driven Hypothesis to Synthesis and Characterization
Université de Montréal(蒙特利尔大学);University of Oxford(牛津大学);University College London(伦敦大学学院);Mila - Québec AI Institute(魁北克人工智能研究所);CIFAR AI Chair(CIFAR人工智能 chair);University of Ottawa(渥太华大学);National Research Council Canada(加拿大国家研究理事会)
Enhancing LLM Reasoning with Reward-guided Tree Search
Gaoling School of Artificial Intelligence, Renmin University of China(中国人民大学高瓴人工智能学院);School of Information, Renmin University of China(中国人民大学信息学院);BAAI(北京智源人工智能研究院);Baichuan AI(百川智能)
Partial Reasoning in Language Models: Search and Refinement Guided by Uncertainty
Advanced Knowledge Center for Immersive Technologies (AKCIT)(沉浸式技术高级知识中心);Federal University of Goiás, Brazil(巴西戈亚斯联邦大学);OATML, University of Oxford(牛津大学OATML)
ReGuLaR: Variational Latent Reasoning Guided by Rendered Chain-of-Thought
Gaoling School of Artificial Intelligence, Renmin University of China(中国人民大学 Gallagher人工智能学院);Beijing Key Laboratory of Research on Large Models(北京大型模型研究关键实验室);Engineering Research Center of Next-Generation Intelligent Search(下一代智能搜索工程研究中心)
LLM-Guided Semantic Relational Reasoning for Multimodal Intent Recognition
Department of Computer Science and Technology, Tsinghua University(清华大学计算机科学与技术系);School of Information Science and Engineering, Hebei University of Science and Technology(河北科技大学信息科学与工程学院)
Lung-R1: A Knowledge Graph-Guided LLM for Pulmonary Diagnostic Reasoning
School of Computer Science, Chongqing University(重庆大学计算机学院);AI Research Institution, Mashang Financial Institution(马上金融人工智能研究院);Department of Information, Third Military Medical University(陆军军医大学信息系)
Think Before You Act: Intention-Guided Reasoning for LLM-Based Location Prediction
The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州));Shanghai Jiao Tong University(上海交通大学);The Hong Kong University of Science and Technology(香港科技大学);Fudan University(复旦大学);Shanghai Innovation Institute(上海创新研究院)