RAMQA: A Unified Framework for Retrieval-Augmented Multi-Modal Question Answering

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Bai, Yang, Grant, Christan Earl, Wang, Daisy Zhe
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866912200924332032
author Bai, Yang
Grant, Christan Earl
Wang, Daisy Zhe
author_facet Bai, Yang
Grant, Christan Earl
Wang, Daisy Zhe
contents Multi-modal retrieval-augmented Question Answering (MRAQA), integrating text and images, has gained significant attention in information retrieval (IR) and natural language processing (NLP). Traditional ranking methods rely on small encoder-based language models, which are incompatible with modern decoder-based generative large language models (LLMs) that have advanced various NLP tasks. To bridge this gap, we propose RAMQA, a unified framework combining learning-to-rank methods with generative permutation-enhanced ranking techniques. We first train a pointwise multi-modal ranker using LLaVA as the backbone. Then, we apply instruction tuning to train a LLaMA model for re-ranking the top-k documents using an innovative autoregressive multi-task learning approach. Our generative ranking model generates re-ranked document IDs and specific answers from document candidates in various permutations. Experiments on two MRAQA benchmarks, WebQA and MultiModalQA, show significant improvements over strong baselines, highlighting the effectiveness of our approach. Code and data are available at: https://github.com/TonyBY/RAMQA
format Preprint
id arxiv_https___arxiv_org_abs_2501_13297
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle RAMQA: A Unified Framework for Retrieval-Augmented Multi-Modal Question Answering
Bai, Yang
Grant, Christan Earl
Wang, Daisy Zhe
Computation and Language
Artificial Intelligence
Information Retrieval
Machine Learning
Multi-modal retrieval-augmented Question Answering (MRAQA), integrating text and images, has gained significant attention in information retrieval (IR) and natural language processing (NLP). Traditional ranking methods rely on small encoder-based language models, which are incompatible with modern decoder-based generative large language models (LLMs) that have advanced various NLP tasks. To bridge this gap, we propose RAMQA, a unified framework combining learning-to-rank methods with generative permutation-enhanced ranking techniques. We first train a pointwise multi-modal ranker using LLaVA as the backbone. Then, we apply instruction tuning to train a LLaMA model for re-ranking the top-k documents using an innovative autoregressive multi-task learning approach. Our generative ranking model generates re-ranked document IDs and specific answers from document candidates in various permutations. Experiments on two MRAQA benchmarks, WebQA and MultiModalQA, show significant improvements over strong baselines, highlighting the effectiveness of our approach. Code and data are available at: https://github.com/TonyBY/RAMQA
title RAMQA: A Unified Framework for Retrieval-Augmented Multi-Modal Question Answering
topic Computation and Language
Artificial Intelligence
Information Retrieval
Machine Learning
url https://arxiv.org/abs/2501.13297