Single Sequence Prediction over Reasoning Graphs for Multi-hop QA

Recent generative approaches for multi-hop question answering (QA) utilize the fusion-indecoder method (Izacard and Grave, 2021) to generate a single sequence output which includes both a final answer and a reasoning path taken to arrive at that answer, such as passage titles and key facts from those passages. While such models can lead to better interpretability and high quantitative scores, they often have difficulty accurately identifying the passages corresponding to key entities in the context, resulting in incorrect passage hops and a lack of faithfulness in the reasoning path. To address this, we propose a single-sequence prediction method over a local reasoning graph (SEQGRAPH) 1 that integrates a graph structure connecting key entities in each context passage to relevant subsequent passages for each question. We use a graph neural network to encode this graph structure and fuse the resulting representations into the entity representations of the model. Our experiments show significant improvements in answer exact-match/F1 scores and faithfulness of grounding in the reasoning path on the HotpotQA dataset and achieve stateof-the-art numbers on the Musique dataset with only up to a 4% increase in model parameters. * Equal contribution 1 Code/Models will be released at https://github.com/ gowtham1997/SeqGraph "An American Werewolf in Paris was a partial sequel to the comedy film starring whom?" An American Werewolf in Paris [f1] It follows the general concept of, and is a loose sequel to, John Landis' 1981 film "An American Werewolf in London".