mlsanityData to 7 Oct 2026

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

arXiv 2512.14770 ↗First posted 16 Dec 2025cs.CV cs.AIcited by 0

On the map: Multimodal LLMs / vision-language models → VLM benchmarks and visual reasoning

Abstract (arXiv)

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 Phi100 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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in VLM benchmarks and visual reasoning, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 5 of its 5 references that are in the map. First posted on arXiv 16 Dec 2025.

Builds on

5 of 5 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024Selective "Selective Prediction": Reducing Unnecessary Abstention in Vision-Language Reasoning23 Feb

Other references · 4

  1. 2024Why are Visually-Grounded Language Models Bad at Image Classification?cited by 101
  2. 2022Reliable Visual Question Answering: Abstain Rather Than Answer Incorrectlycited by 86
  3. 2023Adaptation with Self-Evaluation to Improve Selective Prediction in LLMscited by 49
  4. 2023Improving Selective Visual Question Answering by Learning from Your Peerscited by 24

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Decompose and Compare Consistency: Measuring VLMs' Answer Reliability via Task-Decomposition Consistency Comparison
  2. 2026Verification Mirage: Mapping the Reliability Boundary of Self-Verification in Medical VQA
  3. 2024Uncertainty-Aware Evaluation for Vision-Language Models
  4. 2024SURE-VQA: Systematic Understanding of Robustness Evaluation in Medical VQA Tasks
  5. 2026Uncertainty Is Not a Safety Net for Clinical VQA, but Can It Anticipate Model Failure?
  6. 2026Evaluating VQA in Vision Language Models using Cooperative Principles
  7. 2026Overconfidence and Calibration in Medical VQA: Empirical Findings and Hallucination-Aware Mitigation
  8. 2024TUBench: Benchmarking Large Vision-Language Models on Trustworthiness with Unanswerable Questions