MedLogic-AQA: Enhancing Medical Question Answering with Abstractive Models Focusing on Logical Structures

TL;DR

MedLogic-AQA is a novel abstractive medical question-answering system that integrates first-order logic rules and reasoning to produce more accurate, logical, and comprehensive answers, outperforming existing baselines.

Contribution

This work introduces a new logical reasoning framework within an abstractive QA system, leveraging first-order logic rules and a logic-understanding model for medical questions.

Findings

Outperforms strong baseline models in automated evaluations

Produces logically coherent and relevant answers

Enhances reasoning and informativeness in medical QA

Abstract

In Medical question-answering (QA) tasks, the need for effective systems is pivotal in delivering accurate responses to intricate medical queries. However, existing approaches often struggle to grasp the intricate logical structures and relationships inherent in medical contexts, thus limiting their capacity to furnish precise and nuanced answers. In this work, we address this gap by proposing a novel Abstractive QA system MedLogic-AQA that harnesses First Order Logic (FOL) based rules extracted from both context and questions to generate well-grounded answers. Through initial experimentation, we identified six pertinent first-order logical rules, which were then used to train a Logic-Understanding (LU) model capable of generating logical triples for a given context, question, and answer. These logic triples are then integrated into the training of MedLogic-AQA, enabling effective and coherent reasoning during answer generation. This distinctive fusion of logical reasoning with abstractive QA equips our system to produce answers that are logically sound, relevant, and engaging. Evaluation with respect to both automated and human-based demonstrates the robustness of MedLogic-AQA against strong baselines. Through empirical assessments and case studies, we validate the efficacy of MedLogic-AQA in elevating the quality and comprehensiveness of answers in terms of reasoning as well as informativeness