Self-Correction is More than Refinement: A Learning Framework for Visual and Language Reasoning Tasks
University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Georgia Institute of Technology（佐治亚理工学院）；The Hong Kong University of Science and Technology（香港科技大学）
Jiayi He, Hehai Lin, Qingyun Wang, Yi Fung, Heng Ji
While Vision-Language Models (VLMs) have shown remarkable abilities in visual and language reasoning tasks, they invariably generate flawed responses. Self-correction that instructs models to refine their outputs presents a promising solution to this issue. Previous studies have mainly concentrated on Large Language Models (LLMs), while the self-correction abilities of VLMs, particularly concerning both visual and linguistic information, remain largely unexamined. This study investigates the self-correction capabilities of VLMs during both inference and fine-tuning stages. We introduce a Self-Correction Learning (SCL) approach that enables VLMs to learn from their self-generated self-correction data through Direct Preference Optimization (DPO) without relying on external feedback, facilitating self-improvement. Specifically, we collect preferred and disfavored samples based on the correctness of initial and refined responses, which are obtained by two-turn self-correction with VLMs during the inference stage. Experimental results demonstrate that although VLMs struggle to self-correct effectively during iterative inference without additional fine-tuning and external feedback, they can enhance their performance and avoid previous mistakes through preference fine-tuning when their self-generated self-correction data are categorized into preferred and disfavored samples. This study emphasizes that self-correction is not merely a refinement process; rather, it should enhance the reasoning abilities of models through additional training, enabling them to generate high-quality responses directly without further refinement.
Fine-Tuning on Diverse Reasoning Chains Drives Within-Inference CoT Refinement in LLMs
Ubiquitous Knowledge Processing Lab (UKP Lab), TU Darmstadt and ATHENE National Research Center for Applied Cybersecurity, Germany（图宾根大学知识处理实验室（UKP Lab）及德国应用网络安全国家研究中心ATHENE）；Dept. of ECE & Ingenuity Labs Research Institute, Queen’s University, Canada（皇后大学电子工程系及创新实验室研究机构）；University of Bath, UK（巴斯大学）
RAG-Star: Enhancing Deliberative Reasoning with Retrieval Augmented Verification and Refinement
Gaoling School of Artificial Intelligence, Renmin University of China（中国人民大学高瓴人工智能学院）；Wuhan University of Science and Technology（武汉科技大学）；National University of Singapore（新加坡国立大学）；Northeastern University at Qinhuangdao（东北大学秦皇岛分校）；BOSS Zhipin（BOSS直聘）
Image-of-Thought Prompting for Visual Reasoning Refinement in Multimodal Large Language Models
School of Engineering, Westlake University（西湖大学工程学院）；City University of Hong Kong（香港城市大学）；Research Center for Industries of the Future, Westlake University（西湖大学未来产业研究中心）；Johns Hopkins University（约翰斯·霍普金斯大学）
UniVLR: Unifying Text and Vision in Visual Latent Reasoning for Multimodal LLMs
University of Science and Technology of China（中国科学技术大学）；Tsinghua University（清华大学）；National University of Singapore（新加坡国立大学）；Zhongguancun Academy（中关村学院）
PEIRCE: Unifying Material and Formal Reasoning via LLM-Driven Neuro-Symbolic Refinement
University of Manchester（曼彻斯特大学）；Idiap Research Institute（伊迪亚普研究所）；National Biomarker Centre, CRUK-MI, University of Manchester（英国癌症研究中心曼彻斯特研究所国家生物标志物中心，曼彻斯特大学）；University of Galway（戈尔韦大学）
Phenomenal Yet Puzzling: Testing Inductive Reasoning Capabilities of Language Models with Hypothesis Refinement
Massachusetts Institute of Technology（麻省理工学院）；Allen Institute for Artificial Intelligence（艾伦人工智能研究所）；University of Washington（华盛顿大学）；University of Southern California（南加州大学）
$A^2R^2$: Advancing Img2LaTeX Conversion via Visual Reasoning with Attention-Guided Refinement
University of California, San Diego（加州大学圣地亚哥分校）；ByteDance（字节跳动）；University of California, Merced（加州大学默塞德分校）；University of Southern California（南加州大学）；University at Buffalo（布法罗大学）；The University of Queensland（昆士兰大学）
Zero-Shot Visual Reasoning by Vision-Language Models: Benchmarking and Analysis
ASUS Intelligent Cloud Services (AICS)（华硕智能云服务（AICS））；ASUS Global Pte. Ltd.（华硕全球私人有限公司）；Centre for Frontier AI Research (CFAR)（前沿人工智能研究中心（CFAR））；Institute of High Performance Computing (IHPC)（高性能计算研究所（IHPC））；Agency for Science, Technology and Research (A*STAR)（新加坡科学、技术与研究局（A*STAR））
