RAMQA: A Unified Framework for Retrieval-Augmented Multi-Modal Question Answering
This work addresses a bottleneck in integrating text and images for question answering, offering a domain-specific solution for information retrieval and natural language processing tasks.
The paper tackles the incompatibility between traditional ranking methods and modern generative large language models in multi-modal retrieval-augmented question answering by proposing RAMQA, a unified framework that combines learning-to-rank with generative permutation-enhanced ranking, achieving significant improvements on benchmarks like WebQA and MultiModalQA.
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