paper-with-me

Papers

Multimodal Reranking for Knowledge-Intensive Visual Question Answering

2024-07-17 · Haoyang Wen, Honglei Zhuang, Hamed Zamani, Alexander Hauptmann, Michael Bendersky

Knowledge-intensive visual question answering requires models to effectively use external knowledge to help answer visual questions. A typical pipeline includes a knowledge retriever and an answer generator. However, a retriever that utilizes local information, such as an image patch, may not provide reliable question-candidate relevance scores. Besides, the two-tower architecture also limits the relevance score modeling of a retriever to select top candidates for answer generator reasoning. In this paper, we introduce an additional module, a multi-modal reranker, to improve the ranking quality of knowledge candidates for answer generation. Our reranking module takes multi-modal information from both candidates and questions and performs cross-item interaction for better relevance score modeling. Experiments on OK-VQA and A-OKVQA show that multi-modal reranker from distant supervision provides consistent improvements. We also find a training-testing discrepancy with reranking in answer generation, where performance improves if training knowledge candidates are similar to or noisier than those used in testing.

📄 PDF Abstract BibTeX arXiv:2407.12277

Code (0)

등록된 구현이 없습니다.

Tasks

Answer GenerationQuestion AnsweringRerankingVisual Question AnsweringVisual Question Answering (VQA)

Similar Papers 제목 키워드 기반

Visual-RAG: Benchmarking Text-to-Image Retrieval Augmented Generation for Visual Knowledge Intensive Queries

2025-02-23 · Yin Wu, Quanyu Long, Jing Li, Jianfei Yu 외

Retrieval-Augmented Generation (RAG) is a popular approach for enhancing Large Language Models (LLMs) by addressing their limitations in verifying facts and answering knowledge-intensive questions. As the research in LLM…

BenchmarkingImage RetrievalQuestion AnsweringRAG+2

Passage-specific Prompt Tuning for Passage Reranking in Question Answering with Large Language Models

2024-05-31 · Xuyang Wu, Zhiyuan Peng, Krishna Sravanthi Rajanala Sai, Hsin-Tai Wu 외

Effective passage retrieval and reranking methods have been widely utilized to identify suitable candidates in open-domain question answering tasks, recent studies have resorted to LLMs for reranking the retrieved passag…

Open-Domain Question AnsweringPassage RerankingPassage RetrievalQuestion Answering+1

VisualPuzzles: Decoupling Multimodal Reasoning Evaluation from Domain Knowledge

2025-04-14 · Yueqi Song, Tianyue Ou, Yibo Kong, Zecheng Li 외

Current multimodal benchmarks often conflate reasoning with domain-specific knowledge, making it difficult to isolate and evaluate general reasoning abilities in non-expert settings. To address this, we introduce VisualP…

Logical ReasoningMultimodal ReasoningSpatial ReasoningVisual Reasoning

Salient Knowledge Pathways: Sparse Cross-Modal Routing for Efficient Knowledge-Intensive Multimodal Question Answering

2026-07-28 · Noor Islam S. Mohammad, Uluğ Bayazıt arxiv

Knowledge-intensive multimodal question answering (KI-MMQA) sits at the intersection of three expensive primitives: long visual token sequences, dense retrieval over large external corpora, and full cross-modal fusion. E…

Question Answering

Progressive Multimodal Search and Reasoning for Knowledge-Intensive Visual Question Answering

2025-08-31 · Changin Choi, Wonseok Lee, Jungmin Ko, Wonjong Rhee arxiv

Knowledge-intensive visual question answering (VQA) requires external knowledge beyond image content, demanding precise visual grounding and coherent integration of visual and textual information. Although multimodal ret…

Visual Question AnsweringVisual Grounding