# Exploring LLM-based Data Annotation Strategies for Medical Dialogue Preference Alignment

arXiv: https://arxiv.org/abs/2410.04112 · HTML: https://mlsanity.com/paper/2410.04112/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Medical LLM alignment, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 27 of its 41 references that are in the map.
- First posted on arXiv 5 Oct 2024.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Medical LLM alignment](https://mlsanity.com/alignment/medical-llm-alignment/)

## Builds on (most cited first, 27 of 27)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [GLM: General Language Model Pretraining with Autoregressive Blank Infilling](https://mlsanity.com/paper/2103.10360/) (2021)
- [GLM-130B: An Open Bilingual Pre-trained Model](https://mlsanity.com/paper/2210.02414/) (2022)
- [Baichuan 2: Open Large-scale Language Models](https://mlsanity.com/paper/2309.10305/) (2023)
- [RRHF: Rank Responses to Align Language Models with Human Feedback without tears](https://mlsanity.com/paper/2304.05302/) (2023)
- [MedAlpaca -- An Open-Source Collection of Medical Conversational AI Models and Training Data](https://mlsanity.com/paper/2304.08247/) (2023)
- [On LLMs-Driven Synthetic Data Generation, Curation, and Evaluation: A Survey](https://mlsanity.com/paper/2406.15126/) (2024)
- [HuatuoGPT, towards Taming Language Model to Be a Doctor](https://mlsanity.com/paper/2305.15075/) (2023)
- [HuaTuo: Tuning LLaMA Model with Chinese Medical Knowledge](https://mlsanity.com/paper/2304.06975/) (2023)
- [MedDialog: Two Large-scale Medical Dialogue Datasets](https://mlsanity.com/paper/2004.03329/) (2020)
- [Does Synthetic Data Generation of LLMs Help Clinical Text Mining?](https://mlsanity.com/paper/2303.04360/) (2023)
- [DoctorGLM: Fine-tuning your Chinese Doctor is not a Herculean Task](https://mlsanity.com/paper/2304.01097/) (2023)
- [Zhongjing: Enhancing the Chinese Medical Capabilities of Large Language Model through Expert Feedback and Real-world Multi-turn Dialogue](https://mlsanity.com/paper/2308.03549/) (2023)
- [CMB: A Comprehensive Medical Benchmark in Chinese](https://mlsanity.com/paper/2308.08833/) (2023)
- [HuatuoGPT-II, One-stage Training for Medical Adaption of LLMs](https://mlsanity.com/paper/2311.09774/) (2023)
- [DISC-MedLLM: Bridging General Large Language Models and Real-World Medical Consultation](https://mlsanity.com/paper/2308.14346/) (2023)
- [ClinicalGPT: Large Language Models Finetuned with Diverse Medical Data and Comprehensive Evaluation](https://mlsanity.com/paper/2306.09968/) (2023)
- [Semantic Answer Similarity for Evaluating Question Answering Models](https://mlsanity.com/paper/2108.06130/) (2021)
- [MedDG: An Entity-Centric Medical Consultation Dataset for Entity-Aware Medical Dialogue Generation](https://mlsanity.com/paper/2010.07497/) (2020)
- [A Benchmark for Automatic Medical Consultation System: Frameworks, Tasks and Datasets](https://mlsanity.com/paper/2204.08997/) (2022)
- [A Continued Pretrained LLM Approach for Automatic Medical Note Generation](https://mlsanity.com/paper/2403.09057/) (2024)
- [Effects of diversity incentives on sample diversity and downstream model performance in LLM-based text augmentation](https://mlsanity.com/paper/2401.06643/) (2024)
- [Integrating Physician Diagnostic Logic into Large Language Models: Preference Learning from Process Feedback](https://mlsanity.com/paper/2401.05695/) (2024)
- [PlugMed: Improving Specificity in Patient-Centered Medical Dialogue Generation using In-Context Learning](https://mlsanity.com/paper/2305.11508/) (2023)

## Built on by (most cited first, 1 of 1)

- [A Survey of LLM-based Agents in Medicine: How far are we from Baymax?](https://mlsanity.com/paper/2502.11211/) (2025)

## Abstract (arXiv)

This research examines the use of Reinforcement Learning from AI Feedback (RLAIF) techniques to improve healthcare dialogue models, with the aim of tackling the challenges of preference-aligned data annotation while reducing the reliance on medical experts. We argue that the primary challenges in current RLAIF research for healthcare are the limitations of automated evaluation methods and the difficulties in accurately representing physician preferences. To address these challenges, we present a new evaluation framework based on standardized patient examinations. This framework is designed to objectively assess the effectiveness of large language models (LLMs) in guiding users and following instructions, enabling a comprehensive comparison across different models. Furthermore, our investigation of effective ways to express physician preferences using Constitutional AI algorithms highlighted the particular effectiveness of flowcharts. Utilizing this finding, we introduce an innovative agent-based approach for annotating preference data. This approach autonomously creates medical dialogue flows tailored to the patient's condition, demonstrates strong generalization abilities, and reduces the need for expert involvement. Our results show that the agent-based approach outperforms existing RLAIF annotation methods in standardized patient examinations and surpasses current open source medical dialogue LLMs in various test scenarios.