Dialogue is Better Than Monologue: Instructing Meidcal LLMs via Strategic Conversations (2026.findings-eacl)
Copied to clipboard
Zijie Liu, Xinyu Zhao, Jie Peng, Jinhao Duan, Zhuangdi Zhu, Qingyu Chen, Kaidi Xu, Xia Hu, Tianlong Chen
| Challenge: | Existing tuning methods for medical AI models are monologue-based . existing benchmarks are based on licensing exams or research articles . |
| Approach: | They propose a benchmark to expose limitations of monologue-based tuning for medical AI models . they use a large dialogue dataset to capture stepwise diagnostic reasoning . |
| Outcome: | The proposed model outperforms monologue-tuned models on a medical question answering task and improves accuracy on standard medical QA benchmarks. |
Similar Papers
Reasoning Like a Doctor: Improving Medical Dialogue Systems via Diagnostic Reasoning Process Alignment (2024.findings-acl)
Copied to clipboard
| Challenge: | Medical dialogue systems have attracted significant attention for their potential to act as medical assistants. |
| Approach: | They propose a framework that emulates clinicians' diagnostic reasoning processes and aligns with clinician preferences through thought process modeling. |
| Outcome: | The proposed framework generates appropriate responses that relies on abductive and deductive diagnostic reasoning analyses and aligns with clinician preferences through thought process modeling. |
Do Clinical Question Answering Systems Really Need Specialised Medical Fine Tuning? (2026.eacl-industry)
Copied to clipboard
Sushant Kumar Ray, Gautam Siddharth Kashyap, Sahil Tripathi, Nipun Joshi, Vijay Govindarajan, Rafiq Ali, Jiechao Gao, Usman Naseem
| Challenge: | Clinical Question-Answering (CQA) industry systems rely on Large Language Models (LLMs). |
| Approach: | They propose a framework that applies alignment at inference time rather than through SFT to help CQA users achieve consistent reasoning. |
| Outcome: | MEDASSESS-X improves Accuracy, Factual Consistency and Safety by up to 50%. |
High-Quality Medical Dialogue Synthesis for Improving EMR Generation (2025.emnlp-industry)
Copied to clipboard
| Challenge: | Existing methods for generating EMRs from doctor-patient dialogues produce rigid and repetitive dialogues. |
| Approach: | They propose a framework that integrates Intent Graph Planning, Dual-Agent Simulation and Rule-Reward Quality Control to generate realistic doctor-patient dialogues. |
| Outcome: | The proposed framework significantly enhances realism, diversity and downstream EMR quality, reducing physician editing efforts. |
Leveraging Pretrained Models for Automatic Summarization of Doctor-Patient Conversations (2021.findings-emnlp)
Copied to clipboard
Longxiang Zhang, Renato Negrinho, Arindam Ghosh, Vasudevan Jagannathan, Hamid Reza Hassanzadeh, Thomas Schaaf, Matthew R. Gormley
| Challenge: | Using pretrained transformer models for automatically summarizing doctor-patient conversations presents challenges . limited training data, domain shift, long and noisy transcripts, and high target summary variability are challenges compared to human annotators. |
| Approach: | They propose a method for fine-tuning pretrained transformer models for automatically summarizing doctor-patient conversations directly from transcripts. |
| Outcome: | The proposed method surpasses the performance of an average human annotator and the quality of previous published work for the task. |
Dissecting Clinical Reasoning in Natural Language Inference for Large Language Models (2026.findings-acl)
Copied to clipboard
| Challenge: | Recent studies on large language models (LLMs) have demonstrated the impact of prompting strategies and fine-tuning techniques on their reasoning capabilities. |
| Approach: | They examine four classes of prompting strategies to elicit reasoning in large language models . they then construct demonstrations using a frontier model to distil multi-step reasoning capabilities into smaller models based on Low-Rank Adaptation (LoRA). |
| Outcome: | The proposed model improves in 75% of the models on MedNLI and TREC Clinical Trials. |
Ask Patients with Patience: Enabling LLMs for Human-Centric Medical Dialogue with Grounded Reasoning (2025.emnlp-main)
Copied to clipboard
| Challenge: | a shortage of medical doctors limits access to timely and reliable healthcare . authors propose a multi-turn LLM-based medical assistant for medical inquiries . |
| Approach: | They propose a multi-turn LLM-based medical assistant that asks patients with patience . they compare it with SOTA one-shot and multi-turned LLMs to evaluate its performance . |
| Outcome: | The proposed medical assistant improves diagnostic accuracy, reduces uncertainty and enhances user experience. |
Beyond Fine-tuning: Unleashing the Potential of Continuous Pretraining for Clinical LLMs. (2024.findings-emnlp)
Copied to clipboard
Clement Christophe, Tathagata Raha, Svetlana Maslenkova, Muhammad Umar Salman, Praveenkumar Kanithi, Marco Pimentel, Shadab Khan
| Challenge: | Current approaches to adapting large language models to clinical use-cases are limited. |
| Approach: | They investigate the efficacy of four techniques in adapting large language models for clinical use-cases. |
| Outcome: | The proposed techniques show that they improve performance across clinical tasks. |
Instruct Once, Chat Consistently in Multiple Rounds: An Efficient Tuning Framework for Dialogue (2024.acl-long)
Copied to clipboard
| Challenge: | Tuning language models for dialogue generation has been a prevalent paradigm for building capable dialogue agents. |
| Approach: | They propose a multi-round interactive dialogue tuning framework that models the speaker roles of agent and user separately. |
| Outcome: | The proposed framework performs superior to fine-tuning and improves dialogue consistency. |
Automated Fact-Checking in Dialogue: Are Specialized Models Needed? (2023.emnlp-main)
Copied to clipboard
| Challenge: | Prior work has shown that typical fact-checking models struggle with claims made in conversation. |
| Approach: | They propose to fine-tune models for dialogue on conversational data to improve performance on typical fact-checking. |
| Outcome: | The proposed models perform better on stand-alone claims than state-of-the-art models for dialogue while maintaining their performance on standalone claim. |
CONFIT: Toward Faithful Dialogue Summarization with Linguistically-Informed Contrastive Fine-tuning (2022.naacl-main)
Copied to clipboard
Xiangru Tang, Arjun Nair, Borui Wang, Bingyao Wang, Jai Desai, Aaron Wade, Haoran Li, Asli Celikyilmaz, Yashar Mehdad, Dragomir Radev
| Challenge: | Factual inconsistencies in generated summaries severely limit the practical applications of abstractive dialogue summarization. |
| Approach: | They propose a typology of factual errors to better understand hallucinations generated by current models and a contrastive fine-tuning strategy to improve the factual consistency and overall quality of summaries. |
| Outcome: | The proposed model significantly reduces all kinds of factual errors on both SAMSum dialogue summarization and AMI meeting summarizing datasets. |