用微调代理增强多智能体系统，提升论文主题分析的自动化水平
SFT-TA: Supervised Fine-Tuned Agents in Multi-Agent LLMs for Automated Inductive Thematic Analysis
- 将微调后的智能体嵌入多智能体框架，协同完成主题分析
- 相比GPT-4o基准，与人工标注主题的对齐率显著提高
- 适合需要高精度主题分析的临床研究与自动化质性分析场景
主题分析（TA）是一种广泛使用的定性方法，可为临床访谈转录文本中的模式识别与报告提供结构化但灵活的框架。然而，人工主题分析耗时且难以扩展。近年来大模型的发展为自动化主题分析提供了可能，但与人类结果的对齐度仍有限。为此，我们提出SFT-TA，一种将监督微调（SFT）代理嵌入多智能体系统的自动化主题分析框架。实验表明，该框架在与人工参考主题的对齐度上优于现有方法和GPT-4o基线。尽管SFT代理单独使用时表现不佳，但在多智能体系统中角色分工协作后，性能显著超越基线。结果表明，在多智能体系统中为SFT代理分配特定角色，是提升主题分析输出一致性的重要路径。
原文摘要 · Abstract (English)
Thematic Analysis (TA) is a widely used qualitative method that provides a structured yet flexible framework for identifying and reporting patterns in clinical interview transcripts. However, manual thematic analysis is time-consuming and limits scalability. Recent advances in LLMs offer a pathway to automate thematic analysis, but alignment with human results remains limited. To address these limitations, we propose SFT-TA, an automated thematic analysis framework that embeds supervised fine-tuned (SFT) agents within a multi-agent system. Our framework outperforms existing frameworks and the gpt-4o baseline in alignment with human reference themes. We observed that SFT agents alone may underperform, but achieve better results than the baseline when embedded within a multi-agent system. Our results highlight that embedding SFT agents in specific roles within a multi-agent system is a promising pathway to improve alignment with desired outputs for thematic analysis.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。