paper-with-me

홈 › Papers

Self-Critique Guided Iterative Reasoning for Multi-hop Question Answering

2025-05-25 · Zheng Chu, Huiming Fan, Jingchang Chen, Qianyu Wang, Mingda Yang, Jiafeng Liang, Zhongjie Wang, Hao Li, Guo Tang, Ming Liu, Bing Qin

Although large language models (LLMs) have demonstrated remarkable reasoning capabilities, they still face challenges in knowledge-intensive multi-hop reasoning. Recent work explores iterative retrieval to address complex problems. However, the lack of intermediate guidance often results in inaccurate retrieval and flawed intermediate reasoning, leading to incorrect reasoning. To address these, we propose Self-Critique Guided Iterative Reasoning (SiGIR), which uses self-critique feedback to guide the iterative reasoning process. Specifically, through end-to-end training, we enable the model to iteratively address complex problems via question decomposition. Additionally, the model is able to self-evaluate its intermediate reasoning steps. During iterative reasoning, the model engages in branching exploration and employs self-evaluation to guide the selection of promising reasoning trajectories. Extensive experiments on three multi-hop reasoning datasets demonstrate the effectiveness of our proposed method, surpassing the previous SOTA by $8.6\%$. Furthermore, our thorough analysis offers insights for future research. Our code, data, and models are available at Github: https://github.com/zchuz/SiGIR-MHQA.

📄 PDF Abstract BibTeX arXiv:2505.19112

Code (1)

zchuz/sigir-mhqa 공식 구현 pytorch

Tasks

Multi-hop Question AnsweringQuestion AnsweringRetrieval

Similar Papers 제목 키워드 기반

Double-Checker: Enhancing Reasoning of Slow-Thinking LLMs via Self-Critical Fine-Tuning

2025-06-26 · Xin Xu, Tianhao Chen, Fan Zhang, Wanlong Liu 외

While slow-thinking large language models (LLMs) exhibit reflection-like reasoning, commonly referred to as the "aha moment:, their ability to generate informative critiques and refine prior solutions remains limited. In…

ICRL: Learning to Internalize Self-Critique with Reinforcement Learning

2026-05-13 · Jianbo Lin, Xiaomin Yu, Yi Xin, Yifu Guo 외 arxiv

Large language model-based agents make mistakes, yet critique can often guide the same model toward correct behavior. However, when critique is removed, the model may fail again on the same query, indicating that it has …

Reinforcement LearningMathematical Reasoning

EduFlow: Advancing MLLMs' Problem-Solving Proficiency through Multi-Stage, Multi-Perspective Critique

2025-07-12 · Chenglin Zhu, Tao Zhang, Chong Li, Mingan Lin 외 arxiv

Multimodal large language models (MLLMs) still perform poorly on scientific tasks, particularly those requiring multi-step and interpretable reasoning. Their limitations include insufficient scientific reasoning patterns…

AlignRAG: Leveraging Critique Learning for Evidence-Sensitive Retrieval-Augmented Reasoning

2025-04-21 · Jiaqi Wei, Hao Zhou, Xiang Zhang, Di Zhang 외

Retrieval-augmented generation (RAG) has become a widely adopted paradigm for enabling knowledge-grounded large language models (LLMs). However, standard RAG pipelines often fail to ensure that model reasoning remains co…

RAGRetrievalRetrieval-augmented GenerationText Generation

RealCritic: Towards Effectiveness-Driven Evaluation of Language Model Critiques

2025-01-24 · Zhengyang Tang, Ziniu Li, Zhenyang Xiao, Tian Ding 외

Critiques are important for enhancing the performance of Large Language Models (LLMs), enabling both self-improvement and constructive feedback for others by identifying flaws and suggesting improvements. However, evalua…

Language ModelingLanguage Modelling