AI Paper Atlas

Research map / Vision-language and multimodal / Visual question answering

Prophet: Prompting Large Language Models With Complementary Answer Heuristics for Knowledge-Based Visual Question Answering

Yu Zhou, Xuecheng Ouyang, Zhenwei Shao, Meng Wang, Jun Yu

TPAMI 2025 · Vision-language and multimodal › Visual question answering · approach: Universal VQA models · 53 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
add answer candidates (K=1 vs none) (ablation)Prophet · OK-VQA testaccuracy: 49.63 -> 56.04Improved
increase answer candidates from K=1 to K=10 (ablation)Prophet · OK-VQA testaccuracy: 56.04 -> 60.84Improved
add answer-aware examples (fused features) instead of random examples (ablation)Prophet · OK-VQA testaccuracy: 58.66 -> 60.84Improved
use fused features instead of PICa question+image selection (ablation)Prophet · OK-VQA testaccuracy: 59.82 -> 60.84Improved
add question and image similarity to fused-feature selection (ablation)Prophet · OK-VQA testaccuracy: 60.84 -> 60.38Hurt
select examples by answer logits instead of fused features (ablation)Prophet · OK-VQA testaccuracy: 60.84 -> 60.40Hurt
add in-context examples (N=1 vs N=0, T=5) (ablation)Prophet · OK-VQA testaccuracy: 49.97 -> 56.75Improved
increase queries from T=1 to T=5 at N=16 (ablation)Prophet · OK-VQA testaccuracy: 57.52 -> 60.84Improved
add confidence scores to answer candidates (ablation)Prophet · OK-VQA testaccuracy: 55.46 -> 60.84Improved
add image captions to prompt (ablation)Prophet · OK-VQA testaccuracy: 58.27 -> 60.84Improved
add prompt head (ablation)Prophet · OK-VQA testaccuracy: 60.54 -> 60.84No clear effect
add predicted object tags to prompt (ablation)Prophet · OK-VQA testaccuracy: 60.84 -> 60.51Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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