AlignVQA: Debate-Driven Multi-Agent Calibration for Vision Language Models

Ayush Pandey, Jai Bardhan, Ramya S Hebbalaguppe

Confirmation: I have read and agree with the workshop's policy on behalf of myself and my co-authors.

Keywords: Calibration, VQA, Fine-tuning

TL;DR: Calibration in VQA Tasks

Abstract: In the context of Visual Question Answering (VQA) and Agentic AI, calibration refers to how closely an AI system's confidence in its answers reflects their actual correctness. While modern VQA systems, powered by advanced vision-language models (VLMs), are increasingly used in high-stakes domains like medical diagnostics and autonomous navigation due to their improved accuracy, the reliability of their confidence estimates remains under-examined. Particularly, these systems often produce overconfident responses. To address this, we introduce AlignVQA, a debate-based multi-agent framework, in which diverse specialized VLM -- each following distinct prompting strategies -- generate candidate answers and then engage in two-stage interaction: generalist agents critique, refine and aggregate these proposals. Furthermore, we introduce a novel differentiable calibration-aware loss function called AlignCal designed to fine-tune the specialized agents by minimizing an upper bound on the calibration error. This objective explicitly improves the fidelity of each agent’s confidence estimates. Empirical results across multiple benchmark VQA datasets substantiate the efficacy of our approach, demonstrating substantial reductions in calibration discrepancies.

Submission Track: Workshop Paper Track

Submission Number: 11