Leveraging Structured Information for Explainable Multi-hop Question Answering and Reasoning
This work addresses interpretability and accuracy issues in multi-hop QA for users of neural models, offering a domain-specific incremental improvement.
The paper tackled the problem of inaccurate reasoning and lack of interpretability in multi-hop question answering by leveraging extracted semantic structures (graphs) to generate more faithful reasoning chains, resulting in substantial improvements in QA performance on two benchmark datasets.
Neural models, including large language models (LLMs), achieve superior performance on multi-hop question-answering. To elicit reasoning capabilities from LLMs, recent works propose using the chain-of-thought (CoT) mechanism to generate both the reasoning chain and the answer, which enhances the model's capabilities in conducting multi-hop reasoning. However, several challenges still remain: such as struggling with inaccurate reasoning, hallucinations, and lack of interpretability. On the other hand, information extraction (IE) identifies entities, relations, and events grounded to the text. The extracted structured information can be easily interpreted by humans and machines (Grishman, 2019). In this work, we investigate constructing and leveraging extracted semantic structures (graphs) for multi-hop question answering, especially the reasoning process. Empirical results and human evaluations show that our framework: generates more faithful reasoning chains and substantially improves the QA performance on two benchmark datasets. Moreover, the extracted structures themselves naturally provide grounded explanations that are preferred by humans, as compared to the generated reasoning chains and saliency-based explanations.