AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

Same Person, Different Depiction: Counterfactual Evaluation of Vision-Language Models on Individuals with Limb Deficiencies

Heming Du, Jiaying Ying, Xin Chen, Sen Wang, Xue Li, Xin Yu

ECCV 2026 · Vision-language and multimodal › Multimodal LLMs · approach: VLM capability analysis · 1 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
show limb-deficiency cue in image (vs cue removed)GPT-5 · InclusiveCFImageBiasmean rating shift: −0.089Improved
show limb-deficiency cue in image (vs cue removed)Gemini-2.5 · InclusiveCFImageBiasmean rating shift: −0.404Improved
show limb-deficiency cue in image (vs cue removed)Ministral-3 3B-Reasoning · InclusiveCFImageBiasmean rating shift: +0.071Hurt
show limb-deficiency cue in image (vs cue removed)DeepSeek-VL2 · InclusiveCFImageBiasYes/Unc. decision shift (pp): ∆Yes = −11.90 pp, ∆Unc. = +13.53 ppMixed
use Instruct instead of Thinking variantsQwen3-VL · InclusiveCFImageBiascue sensitivity (rating, regard)Improved
keep limb cue visible in edit control (same-cue edit) (ablation)Qwen-Image-Edit pipeline · InclusiveCFImageBiasrating shift: −0.151 -> −0.152No clear effect
same-cue edit control (ablation)Qwen-Image-Edit pipeline · InclusiveCFImageBiasYes-rate shift (pp): −3.58 pp -> −1.77 ppMixed
restrict to single-person pairs (ablation)benchmark analysis · InclusiveCFImageBias (392 single-person pairs)rating shift: −0.151 -> −0.169Improved
restrict to multi-person pairs (ablation)benchmark analysis · InclusiveCFImageBias (70 multi-person pairs)rating shift: −0.042No clear effect
compare original vs counterfactual instead of repeat of same input (ablation)benchmark analysis · InclusiveCFImageBiasrating change: 0.122 -> 0.314Hurt
compare original vs counterfactual instead of repeat of same input (ablation)benchmark analysis · InclusiveCFImageBiasdecision TVD (pp): 1.81 pp -> 8.89 ppHurt
remove limb cue from imageVLMs · InclusiveCFImageBiasevaluative term frequency: 0.528 -> 0.396Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy