VDebugger: Harnessing Execution Feedback for Debugging Visual Programs
Xueqing Wu, Zongyu Lin, Songyan Zhao, Te-Lin Wu, Pan Lu, Nanyun Peng, and Kai-Wei Chang, in Proceedings of the Findings of ACL at The 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP-Findings), 2024.
Download the full text
Abstract
Visual programs are executable code generated by large language models to address visual reasoning problems. They decompose complex questions into multiple reasoning steps and invoke specialized models for each step to solve the problems. However, these programs are prone to logic errors, with our preliminary evaluation showing that 58% of the total errors are caused by program logic errors. Debugging complex visual programs remains a major bottleneck for visual reasoning. To address this, we introduce VDebugger, a novel critic-refiner framework trained to localize and debug visual programs by tracking execution step by step. VDebugger identifies and corrects program errors leveraging detailed execution feedback, improving interpretability and accuracy. The training data is generated through an automated pipeline that injects errors into correct visual programs using a novel mask-best decoding technique. Evaluations on six datasets demonstrate VDebugger’s effectiveness, showing performance improvements of up to 3.2% in downstream task accuracy. Further studies show VDebugger’s ability to generalize to unseen tasks, bringing a notable improvement of 2.3% on the unseen COVR task.
Bib Entry
@inproceedings{wu2024vdebugger,
author = {Wu, Xueqing and Lin, Zongyu and Zhao, Songyan and Wu, Te-Lin and Lu, Pan and Peng, Nanyun and Chang, Kai-Wei},
title = {VDebugger: Harnessing Execution Feedback for Debugging Visual Programs},
booktitle = {Proceedings of the Findings of ACL at The 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP-Findings)},
year = {2024}
}