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.
@article{arxiv.2509.17167,
title = {SFT-TA: Supervised Fine-Tuned Agents in Multi-Agent LLMs for Automated Inductive Thematic Analysis},
author = {Seungjun Yi and Joakim Nguyen and Huimin Xu and Terence Lim and Joseph Skrovan and Mehak Beri and Hitakshi Modi and Andrew Well and Liu Leqi and Mia Markey and Ying Ding},
journal= {arXiv preprint arXiv:2509.17167},
year = {2025}
}