Lune

EMNLP Findings2024

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

Aizan Zafar, Kshitij Mishra, Asif Ekbal

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 wellgrounded 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 1 .

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

1 top-tier paper has cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers1

  1. HalluCitation Matters: Revealing the Impact of Hallucinated References with 300 Hallucinated Papers in ACL ConferencesYusuke Sakai, Hidetaka Kamigaito, Taro WatanabeACL 2026 · 18 citations

Builds on3

  1. BioMistral: A Collection of Open-Source Pretrained Large Language Models for Medical DomainsYanis Labrak, Adrien Bazoge, Emmanuel Morin, Pierre-Antoine Gourraud et al.ACL Findings 2024 · 271 citations
  2. Question Answering with Long Multiple-Span AnswersMing Zhu, Aman Ahuja, Da-Cheng Juan, Wei Wei et al.EMNLP Findings 2020 · 63 citations
  3. CDialog: A Multi-turn Covid-19 Conversation Dataset for Entity-Aware Dialog GenerationDeeksha Varshney, Aizan Zafar, Niranshu Kumar Behra, Asif EkbalEMNLP 2022 · 2 citations

Related papers

  1. Integrating Deep Learning with Logic Fusion for Information ExtractionWenya Wang, Sinno Jialin PanAAAI 2020 · 55 citations
  2. Enhancing Complex Reasoning in Knowledge Graph Question Answering through Query Graph ApproximationHongjun Jeong, Minji Kim, Heesoo Jung, Ko Keun Kim et al.ACL Findings 2025 · 3 citations
  3. Deep Inductive Logic Reasoning for Multi-Hop Reading ComprehensionWenya Wang, Sinno Jialin PanACL 2022 · 19 citations
  4. MedLA: A Logic-Driven Multi-Agent Framework for Complex Medical Reasoning with Large Language ModelsSiqi Ma, Jiajie Huang, Fan Zhang, Jinlin Wu et al.AAAI 2026 · 10 citations
  5. Agentic Medical Knowledge Graphs Enhance Medical Question Answering: Bridging the Gap Between LLMs and Evolving Medical KnowledgeMohammad R. Rezaei, Reza Saadati Fard, Jayson Parker, Rahul G. Krishnan et al.EMNLP Findings 2025 · 14 citations
Dusk over the sea between two cliffs drawn in fine vertical lines