Enhancing Multi-modal and Multi-hop Question Answering via Structured Knowledge and Unified Retrieval-Generation
This addresses the challenge of connecting diverse sources in QA for AI applications, though it is incremental as it builds on existing retrieval-generation methods.
The paper tackled the problem of multi-modal multi-hop question answering by proposing SKURG, which integrates retrieval and generation, resulting in state-of-the-art performance on datasets like MultimodalQA and WebQA with fewer parameters.
Multi-modal multi-hop question answering involves answering a question by reasoning over multiple input sources from different modalities. Existing methods often retrieve evidences separately and then use a language model to generate an answer based on the retrieved evidences, and thus do not adequately connect candidates and are unable to model the interdependent relations during retrieval. Moreover, the pipelined approaches of retrieval and generation might result in poor generation performance when retrieval performance is low. To address these issues, we propose a Structured Knowledge and Unified Retrieval-Generation (SKURG) approach. SKURG employs an Entity-centered Fusion Encoder to align sources from different modalities using shared entities. It then uses a unified Retrieval-Generation Decoder to integrate intermediate retrieval results for answer generation and also adaptively determine the number of retrieval steps. Extensive experiments on two representative multi-modal multi-hop QA datasets MultimodalQA and WebQA demonstrate that SKURG outperforms the state-of-the-art models in both source retrieval and answer generation performance with fewer parameters. Our code is available at https://github.com/HITsz-TMG/SKURG.