Self-Correction is More than Refinement: A Learning Framework for Visual and Language Reasoning Tasks
Year: 2025
Type: conference-paper
Abstract: While Vision-Language Models (VLMs) have shown remarkable abilities, 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.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 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 models' reasoning ability through additional training, enabling them to generate high-quality responses directly without further refinement. 1
Authors: Jiayi He, Hehai Lin, Qingyun Wang, Yi R. Fung, Heng Ji
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: gold
OpenAlex ID: W4412888604