AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

Gender Bias in Vision-Language In-Context Learning

Tong Xiang, Yuta Nakashima, Noa Garcia

ECCV 2026 · Vision-language and multimodal › Multimodal LLMs · approach: VLM capability analysis · 0 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
use male-only demonstrations instead of random (ablation)LVLM ICL · captioning and pronoun predictionER_m-fImproved
use female-only demonstrations instead of random (ablation)LVLM ICL · captioning and pronoun predictionER_m-f: -27.5 -> 27.2 (MiniCPM, VisoGender-OO 8-shot)Hurt
use gendered (single-gender) demonstrations (ablation)LVLM ICL · VisoGender-OP 8-shotopposite-gender error rate: ER_f 9.7 (FS) -> 85.5 (MS), Qwen-VLHurt
use gendered demonstrations (ablation)LVLM ICL · VQA (VisualCoT)ER_m-f: differs by at most 1.82 across settingsNo clear effect
use similarity-based retrieval (SIIR/SITR) instead of random selectionLVLM ICL · COCOBias captioning 8-shotER_m-f: -1.01 (RS) -> -2.25 (SIIR), -2.35 (SITR), Phi-3.5-visionHurt
use a gender-balanced pool for similarity retrieval (ablation)SIIR/SITR · COCOBias captioningER_m-fMixed
use balanced demonstrations (BS) instead of random (ablation)LVLM ICL · COCOBias captioning 8-shotER_m-f: -1.01 -> -0.75 (Phi-3.5-vision)Improved
vary gender composition of demonstrations (ablation)LVLM ICL · COCOBias captioningCLIPScore/BLEU-4: CLIPScore range at most 0.67No clear effect
replace real in-context images with synthetic FLUX/SD3.5L images (ablation)LVLM ICL · COCOBias captioning MS/FS|ER_m-f| on revealed samples: Phi-3.5-vision MS 4-shot 2.24 -> gap -0.36 (FLUX)Improved
replace real in-context images with synthetic images (ablation)LVLM ICL · COCOBias captioningCLIPScore: differences within 0.5No clear effect
replace real in-context images with synthetic images (ablation)LVLM ICL · COCOBias captioningreveal rateHurt

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