Multi-Granularity Guided Fusion-in-Decoder

arXiv:2404.02581v1 Announce Type: new
Abstract: In Open-domain Question Answering (ODQA), it is essential to discern relevant contexts as evidence and avoid spurious ones among retrieved results. The model architecture that uses concatenated multiple contexts in the decoding phase, i.e., Fusion-in-Decoder, demonstrates promising performance but generates incorrect outputs from seemingly plausible contexts. To address this problem, we propose the Multi-Granularity guided Fusion-in-Decoder (MGFiD), discerning evidence across multiple levels of granularity. Based on multi-task learning, MGFiD harmonizes passage re-ranking with sentence classification. …

abstract architecture arxiv cs.cl cs.ir decoder decoding domain evidence fusion multiple performance question question answering results type