AI Paper Atlas

Research map / Vision-language and multimodal / CLIP and zero-shot

PRISM: Reducing Spurious Implicit Biases in Vision-Language Models with LLM-Guided Embedding Projection

Mahdiyar Molahasani, Azadeh Motamedi, Michael Greenspan, Il-Min Kim, Ali Etemad

ICCV 2025 · Vision-language and multimodal › CLIP and zero-shot · approach: Self-distillation for vision-language pretraining · 3 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
Replace orthogonal projection (PRISM-mini) with learned projection trained by LD loss (ablation)PRISM · Waterbirdsworst-group accuracy: 69.5% -> 84.2%Improved
Replace orthogonal projection (PRISM-mini) with learned projection trained by LD loss (ablation)PRISM · CelebAworst-group accuracy: 82.6% -> 84.0%Improved
Apply PRISM debiasing projection to zero-shot CLIP-ViT-L/14CLIP-ViT-L/14 · Waterbirdsworst-group accuracy: 36.4% -> 84.2%Improved
Apply PRISM debiasing projection to zero-shot CLIP-ViT-L/14CLIP-ViT-L/14 · CelebAworst-group accuracy: 72.8% -> 84.0%Improved
Apply PRISM to CLIP-RN50CLIP-RN50 · Waterbirdsworst-group accuracy: 38.3% -> 70.2%Improved
Apply PRISM to CLIP-RN50CLIP-RN50 · CelebAworst-group accuracy: 75.8% -> 83.3%Improved
Use GPT 4o instead of Llama 3.2 (70B) as the LLM (ablation)PRISM · CelebAworst-group accuracy: 58.9% -> 84.0%Improved
Use GPT 4o instead of GPT 4o mini as the LLM (ablation)PRISM · CelebAworst-group accuracy: 81.6% -> 84.0%Improved
Use GPT 4o instead of GPT o1 as the LLM (ablation)PRISM · CelebAworst-group accuracy: 77.9% -> 84.0%Improved
Use PRISM instead of Orth-Cali on CLIP-RN50PRISM · Waterbirds (CLIP-RN50)worst-group accuracy: 74.0% -> 70.2%Hurt
Evaluate scene descriptions in text instead of images (bias similarity)CLIP zero-shot · Waterbirdsworst-group accuracy: 38.3% -> 33.1%No clear effect
Set margin m to 0.6 in LD loss (ablation)PRISM · Waterbirds and CelebAworst-group accuracyImproved

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