Research map / Vision-language and multimodal / Visual question answering
EntRAG: Entity-Centric Retrieval-Augmented Generation for Knowledge-based Visual Question Answering
Yiheng Hu, Xiaoyang Wang, Qing Liu, Xiwei Xu, Qian Fu, Wenjie Zhang
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 changed | Where | Measured | Effect |
|---|---|---|---|
| use entity-conditioned visual processor instead of CLIP visual encoder (ablation) | EntBind · E-VQA entity retrieval | R@1: 42.4 -> 57.0 | Improved |
| use entity-guided attention pooling instead of learned-weight pooling (ablation) | EntBind · E-VQA entity retrieval | R@1: 53.4 -> 57.0 | Improved |
| add visual embedding (visual processor) (ablation) | EntBind · E-VQA entity retrieval | R@1: 21.0 -> 57.0 | Improved |
| add entity token embedding (ablation) | EntBind · E-VQA entity retrieval | R@1: 51.4 -> 57.0 | Improved |
| combine similarity and relevance scores for entity ranking (ablation) | ECRanker · E-VQA entity-level | R@1: 62.8 -> 78.0 | Improved |
| rank contexts within top-ranked entity (Entity-First) instead of pooled contexts (ablation) | ECRanker · E-VQA context-level | R@1: 59.4 -> 68.0 | Improved |
| use joint score instead of Entity-First for context ranking (ablation) | ECRanker · E-VQA context-level | R@1: 68.0 -> 62.3 | Hurt |
| Entity-Pool instead of Entity-First ranking (ablation) | ECRanker · E-VQA context-level | R@5: 77.4 -> 81.2 (R@5), 68.0 -> 59.4 (R@1) | Mixed |
| use EntBind alone for context-level ranking (ablation) | EntBind · E-VQA context-level | R@1: 68.0 -> 6.8 | Hurt |
| use CAGen with oracle context (ablation) | LLaVA-v1.6-7B · E-VQA oracle retrieval | VQA accuracy: 78.1 -> 88.7 | Improved |
| entity-centric retrieval with EntBind instead of MM-Embed | EntRAG · InfoSeek entity retrieval | R@1: 36.7 -> 58.5 | Improved |
| swap generator backbone from LLaVA-v1.5 to Qwen-2.5 | EntRAG · InfoSeek (All) | VQA accuracy: 40.3 -> 44.5 | Improved |
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.
- MM-Embed — MM-EMBED: UNIVERSAL MULTIMODAL RETRIEVAL WITH MULTIMODAL LLMS (ICLR 2025) · better on 2 of 2 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
- Retrieval-Augmented Visual Question Answering via Built-in Autoregressive Search Engines (AAAI 2025 · similarity 0.91)
- VTQA: Visual Text Question Answering via Entity Alignment and Cross-Media Reasoning (CVPR 2024 · similarity 0.89)
- Separation of Powers: On Segregating Knowledge from Observation in LLM-enabled Knowledge-based Visual Question Answering (CVPR 2025 · similarity 0.88)
- SK-VQA: Synthetic Knowledge Generation at Scale for Training Context-Augmented Multimodal LLMs (ICML 2025 · similarity 0.88)
- ConVQG: Contrastive Visual Question Generation with Multimodal Guidance (AAAI 2024 · similarity 0.88)
- Re-ranking Reasoning Context with Tree Search Makes Large Vision-Language Models Stronger (ICML 2025 · similarity 0.87)
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.
