EDCT-Bench: Uncovering Faithfulness Gaps in VLMs via Explanation-Driven Counterfactual Testing
This story is from 2026-09-17. It is preserved in the archive; the latest stories are on the live feed.
arXiv:2609.17953v1 Announce Type: new Abstract: Vision-Language Models (VLMs) can produce Natural Language Explanations (NLEs) that sound plausible yet remain inconsistent with the visual evidence they cite. We present Explanation-Driven Counterfactual Testing (EDCT), an intervention-based protocol…
Read the full story at arXiv cs.CV ↗
Timeline · 1 report
- 2026-09-17 04:00 · arXiv cs.CV
EDCT-Bench: Uncovering Faithfulness Gaps in VLMs via Explanation-Driven Counterfactual Testing