← Back to all news
arXiv AI By Sihao Ding, Santosh Vasa, Aditi Ramadwar, Thomas Monninger

EDCT-Bench: Uncovering Faithfulness Gaps in VLMs via Explanation-Driven Counterfactual Testing

Read the original on arXiv AI →

EDCT-Bench is a benchmark that evaluates the faithfulness of Vision‑Language Models (VLMs) by using Explanation‑Driven Counterfactual Testing (EDCT). EDCT extracts visual concepts from a model’s natural language explanation, applies minimal verified edits to those concepts, and checks whether the model’s answer and explanation remain consistent with the edited image. The benchmark covers three domains—knowledge‑intensive VQA, safety‑critical driving, and 3D spatial reasoning—and reveals significant faithfulness gaps in current VLMs, while also showing that EDCT‑generated counterfactuals can improve training.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv AI
Jul 21

Seeing What Is Actually There: PriVE-Bench and PriVE-Tools for Counterfactual Evaluation of Agentic Visual Evidence in VLMs

arXiv:2607. 16311v1 Announce Type: cross Abstract: Vision-language models (VLMs) often answer visual questions using learned language and category priors rather than grounding their predictions in the image itself.

By Jingyu Sun, Jiachen Tu, Yuyang Xue, Yaoxin Jiang, Guoyi Xu, Zhengtao Yao, Rui Qian, Yizheng Sun, Hongpeng Zhou, Jingyuan Sun, Yan Lin
llmsagentsmultimodalbenchmarks
More like this →
arXiv AI
Sep 10

Counterfactual Tests for Measuring Chain-of-Thought Faithfulness in Visual Language Models

The paper introduces visual adaptations of counterfactual tests—vCT and vCCT—to evaluate whether chain-of-thought explanations in vision‑language models faithfully reflect the visual evidence driving predictions. Using these tests, the authors benchmark eight open‑source VLMs on two datasets and find that CoTs often fail to track visual evidence, sometimes omitting removed objects or mentioning them inconsistently. They also release two new datasets, Counter‑SNLI‑VE and Counter‑A‑OKVQA, consisting of image pairs that differ by a single object to facilitate further research.

By Bayar Menzat, Maximilian S\"uss, Ruizhi Wang, Benno Steinegger, Thomas Lukasiewicz, Oana-Maria Camburu
llmsbenchmarks
More like this →