# Improving VQA Reliability: A Dual-Assessment Approach with Self-Reflection and Cross-Model Verification

Source: [Improving VQA Reliability: A Dual-Assessment Approach with Self-Reflection and Cross-Model Verification](<https://www.sota2.com/research/paper/69438a89423ea42265729455>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-12-19T05:00:04.527Z

Authors: Xixian Wu, Yang Ou, Pengchao Tian, Zian Yang, Jielei Zhang, Peiyi Li, Longwen Gao

Published: 2025-12-16T09:24:42.000Z

## Abstract

Vision-language models (VLMs) have demonstrated significant potential in Visual Question Answering (VQA). However, the susceptibility of VLMs to hallucinations can lead to overconfident yet incorrect answers, severely undermining answer reliability. To address this, we propose Dual-Assessment for VLM Reliability (DAVR), a novel framework that integrates Self-Reflection and Cross-Model Verification for comprehensive uncertainty estimation. The DAVR framework features a dual-pathway architecture: one pathway leverages dual selector modules to assess response reliability by fusing VLM latent features with QA embeddings, while the other deploys external reference models for factual cross-checking to mitigate hallucinations. Evaluated in the Reliable VQA Challenge at ICCV-CLVL 2025, DAVR achieves a leading $\\Phi\_{100}$ score of 39.64 and a 100-AUC of 97.22, securing first place and demonstrating its effectiveness in enhancing the trustworthiness of VLM responses.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Visual Question Answering on VQA Reliable Challenge v2 (test-standard)](<https://www.sota2.com/research/sota/visual-question-answering-on-vqa-reliable-challenge-v2-test-standard.md>): Visual Question Answering; VQA Reliable Challenge v2 (test-standard); Accuracy: 84.11.

- [Visual Question Answering on VQAv2 Reliable Challenge (test-dev)](<https://www.sota2.com/research/sota/visual-question-answering-on-vqav2-reliable-challenge-test-dev.md>): Visual Question Answering; VQAv2 Reliable Challenge (test-dev); Accuracy: 83.99.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2512.14770>)

[PDF](<https://arxiv.org/pdf/2512.14770.pdf>)