AI Paper Atlas

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

Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language

Andy Zeng, Maria Attarian, brian ichter, Krzysztof Marcin Choromanski, Adrian Wong, Stefan Welker, Federico Tombari, Aveek Purohit, Michael S Ryoo, Vikas Sindhwani, Johnny Lee, Vincent Vanhoucke and 1 more

ICLR 2023 · Vision-language and multimodal › CLIP and zero-shot · approach: Language models for zero-shot reasoning · 169 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
Compose CLIP image information with GPT-3 caption generation and CLIP rerankingZeroCap on MS COCO Captions · MS COCO Captions test subset (100 images)CIDEr: 18.0 -> 44.5Improved
Add 3 training captions to the prompt (ablation)Socratic Models on MS COCO Captions · MS COCO Captions test subset (100 images)CIDEr: 44.5 -> 76.3Improved
Compose CLIP image information with GPT-3 caption generationKreiss et al. on Concadia · Concadia testCIDEr (caption generation): 11.3 -> 38.9Improved
Compose CLIP image information with GPT-3 description generationKreiss et al. on Concadia · Concadia testCIDEr (description generation): 17.4 -> 22.6Improved
Remove VLM image information (ablation)Socratic Models on Concadia · Concadia testCIDEr (caption generation): 38.9 -> 40.1Improved
Remove VLM image information (ablation)Socratic Models on Concadia · Concadia testCIDEr (description generation): 22.6 -> 20.6Hurt
Add the ground-truth image description as input (ablation)Socratic Models on Concadia · Concadia testCIDEr (caption generation): 93.8Improved
Add audio transcripts and language-based transcript reasoning to CLIP retrievalCLIP via Portillo-Quintero et al. on MSR-VTT Full · MSR-VTT FullR@1: 40.3 -> 44.7Improved
Use transcript-based reasoning for videos with long transcriptsCLIP via Portillo-Quintero et al. on MSR-VTT Full · MSR-VTT Full, long-transcript subsetR@1: 41.5 -> 54.9Improved
Add audio transcripts and language-based transcript reasoning to CLIP retrievalCLIP via Portillo-Quintero et al. on MSR-VTT 1k-A · MSR-VTT 1k-AR@1: 58.0 -> 60.7Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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