DocTalk: Enhancing Medical Knowledge Retrieval via Fine-tuned Large Language Models with Chain-of-Thought Reasoning for Robust Clinical Decision Support

Asad Gohar; Md Ariful Islam Mozumder; Moon-Il Joo; Hee-Cheol Kim

cs.AIOct 26, 2026

DocTalk: Enhancing Medical Knowledge Retrieval via Fine-tuned Large Language Models with Chain-of-Thought Reasoning for Robust Clinical Decision Support

Authors: Asad Gohar, Md Ariful Islam Mozumder, Moon-Il Joo, Hee-Cheol Kim

Organizations: Institute of Digital Anti-Aging HealthCare, Inje University, Gimhae 50834, Republic of Korea

Abstract

Objective: The rapid advancement of large language models (LLMs) in healthcare has opened new possibilities for AI-assisted clinical decision-making; however, safe and effective deployment remains challenging because of hallucination and domain misalignment. This study introduces DocTalk, a doctor-assistive question-answering (QA) system designed to generate concise, chart-grounded responses from de-identified discharge summaries. Methods: We developed a high-fidelity data generation pipeline that produces 500 clinically relevant QA pairs through sentence-level decomposition, chain-of-thought-guided question formulation, and expert review. Six open-source LLMs, including three general-purpose and three biomedical models, were evaluated before and after parameter-efficient instruction tuning using Low-Rank Adaptation (LoRA). The framework integrates prompt engineering, in-context learning, and medically aligned evaluation to support factual and interpretable responses. Results: On DocTalk-QA, instruction tuning produced consistent improvements across lexical, semantic, and clinical fidelity metrics. The best-performing tuned model, Llama-3-Med42-8B, achieved ROUGE-L = 0.40, BERTScore-F1 = 0.76, and UMLS-F1 = 0.49. To examine external generalization beyond the DocTalk-QA dataset, the two best-performing models, Llama-3.1-8B-Instruct and Llama-3-Med42-8B, were evaluated on PubMedQA before and after instruction tuning. Accuracy improved from 0.931 to 0.977 for Llama-3.1-8B-Instruct and from 0.935 to 0.943 for Llama-3-Med42-8B. Conclusion: DocTalk was deployed as a secure web-based platform for interactive EHR querying. These findings suggest that clinically grounded instruction tuning can improve medical QA performance and support practical clinical decision support.

Clinical QA

Clinical question answering uses AI to answer medical and patient-specific questions from clinical knowledge, records, guidelines, and evidence.

See all 62 papers

Medical Fine-Tuning Reshapes, Not Reduces, Patient-Facing AI Risk: A Rubric-Based, LLM-Judge Evaluation Framework
Oct 17, 2026Savan DoshiLanguage Model Safety Evaluation Medical QA
Multilingual Medical Reasoning for Question Answering with Large Language Models
Dec 5, 2025Pietro Ferrazzi, Aitor Soroa, Rodrigo AgerriKnowledge Augmentation for Language Models Healthcare
Fondazione Bruno Kessler, Trento, Italy · HiTZ Center - Ixa, University of the Basque Country EHU, Spain
SDoH-Aware Narrative Anchoring Bias in Medical LLMs for Trustworthy Clinical Decision Support
Aug 24, 2026Ahnaf Atef Choudhury, Ramkrishna SahaMedical LLMs Language Model Bias Evaluation
Department of Information Sciences and Technology George Mason University, USA · Department of Computer Science The University of Texas at Dallas, USA

Oct 17, 2026J/K move · Enter open · S save

Medical Fine-Tuning Reshapes, Not Reduces, Patient-Facing AI Risk: A Rubric-Based, LLM-Judge Evaluation Framework

Savan Doshi

Language Model Safety Evaluation Medical QA

Open paper AskPDF arXiv

Patient-facing medical question answering with large language models (LLMs) is moving from research demonstrations to production deployments, yet evaluation remains anchored on factual correctness. Factuality is necessary but not sufficient: a response can be factually grounded and still issue a directive that, if acted on, would harm the patient. We introduce a risk-sensitive evaluation framework that scores responses by the presence and severity of six categories of risk-bearing language (treatment directives, contraindications, dosage expressions, urgency-triage cues, high-alert medication mentions, and overconfident assertions), anchored on published clinical harm taxonomies. Severity is classified by a three-judge LLM ensemble. We apply this framework to six 7-9B instruction-tuned models, three general (Mistral-7B, Phi-3.5-mini, Llama-3.1-8B) and three medically adapted (BioMistral-7B, OpenBioLLM-Llama3-8B, Med42-Llama3-8B), on 200 real patient questions from the K-QA benchmark. Two findings emerge. First, ensemble risk-bearing language is statistically independent of factual hallucination rate (pooled Spearman

ρ= -0.065

n = 300

, 95% CI

[-0.18, +0.05]

; distance correlation

= 0.10

, independence test

p = 0.24

). Second, medical fine-tuning does not reduce aggregate risk but reshapes it: continued-pretraining adaptations (BioMistral, OpenBioLLM) consistently suppress high-alert medication mentions while amplifying overconfident assertions, whereas clinical instruction-tuning (Med42) suppresses dosing only, without amplifying overconfidence. Per-category Krippendorff

α

is fair to good for the four linguistically anchored categories (0.53-0.71) and low for the two clinical-judgment-dependent categories (0.19, 0.31), indicating where automatic safety evaluation is and is not yet reliable. We release the rubric, judge prompts, and evaluation code.

Abstract

Clinical QA

Explore similar work

Medical Fine-Tuning Reshapes, Not Reduces, Patient-Facing AI Risk: A Rubric-Based, LLM-Judge Evaluation Framework

Multilingual Medical Reasoning for Question Answering with Large Language Models

SDoH-Aware Narrative Anchoring Bias in Medical LLMs for Trustworthy Clinical Decision Support