Triplet-Structured Knowledge Integration for Multi-Turn Medical Reasoning
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866915552511918080 |
|---|---|
| author | Meng, Zhaohan Meng, Zaiqiao Liu, Siwei Ounis, Iadh |
| author_facet | Meng, Zhaohan Meng, Zaiqiao Liu, Siwei Ounis, Iadh |
| contents | Large Language Models (LLMs) have shown strong performance on static medical Question Answering (QA) tasks, yet their reasoning often deteriorates in multi-turn clinical dialogues where patient information is scattered across turns. This paper introduces TriMediQ, a triplet-structured approach that enhances the reasoning reliability of LLMs through explicit knowledge integration. TriMediQ first employs a frozen triplet extraction LLM to convert patient responses into clinically grounded triplets, ensuring factual precision via constrained prompting. These triplets are incorporated into a patient-specific Knowledge Graph (KG), from which a trainable projection module consisting of a graph encoder and a projector captures relational dependencies while keeping all LLM parameters frozen. During inference, the projection module guides multi-hop reasoning over the KG, enabling coherent clinical dialogue understanding. Experiments on two interactive medical QA benchmarks show that TriMediQ achieves up to 10.4\% improvement in accuracy over five existing baselines on the iMedQA dataset. These results demonstrate that structuring patient information as triplets can effectively improve the reasoning capability of LLMs in multi-turn medical QA. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_03536 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Triplet-Structured Knowledge Integration for Multi-Turn Medical Reasoning Meng, Zhaohan Meng, Zaiqiao Liu, Siwei Ounis, Iadh Computation and Language Artificial Intelligence Large Language Models (LLMs) have shown strong performance on static medical Question Answering (QA) tasks, yet their reasoning often deteriorates in multi-turn clinical dialogues where patient information is scattered across turns. This paper introduces TriMediQ, a triplet-structured approach that enhances the reasoning reliability of LLMs through explicit knowledge integration. TriMediQ first employs a frozen triplet extraction LLM to convert patient responses into clinically grounded triplets, ensuring factual precision via constrained prompting. These triplets are incorporated into a patient-specific Knowledge Graph (KG), from which a trainable projection module consisting of a graph encoder and a projector captures relational dependencies while keeping all LLM parameters frozen. During inference, the projection module guides multi-hop reasoning over the KG, enabling coherent clinical dialogue understanding. Experiments on two interactive medical QA benchmarks show that TriMediQ achieves up to 10.4\% improvement in accuracy over five existing baselines on the iMedQA dataset. These results demonstrate that structuring patient information as triplets can effectively improve the reasoning capability of LLMs in multi-turn medical QA. |
| title | Triplet-Structured Knowledge Integration for Multi-Turn Medical Reasoning |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2510.03536 |