SFT-TA: Supervised Fine-Tuned Agents in Multi-Agent LLMs for Automated Inductive Thematic Analysis

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yi, Seungjun, Nguyen, Joakim, Xu, Huimin, Lim, Terence, Skrovan, Joseph, Beri, Mehak, Modi, Hitakshi, Well, Andrew, Leqi, Liu, Markey, Mia, Ding, Ying
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911167918637056
author Yi, Seungjun
Nguyen, Joakim
Xu, Huimin
Lim, Terence
Skrovan, Joseph
Beri, Mehak
Modi, Hitakshi
Well, Andrew
Leqi, Liu
Markey, Mia
Ding, Ying
author_facet Yi, Seungjun
Nguyen, Joakim
Xu, Huimin
Lim, Terence
Skrovan, Joseph
Beri, Mehak
Modi, Hitakshi
Well, Andrew
Leqi, Liu
Markey, Mia
Ding, Ying
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2509_17167
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SFT-TA: Supervised Fine-Tuned Agents in Multi-Agent LLMs for Automated Inductive Thematic Analysis
Yi, Seungjun
Nguyen, Joakim
Xu, Huimin
Lim, Terence
Skrovan, Joseph
Beri, Mehak
Modi, Hitakshi
Well, Andrew
Leqi, Liu
Markey, Mia
Ding, Ying
Computation and Language
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.
title SFT-TA: Supervised Fine-Tuned Agents in Multi-Agent LLMs for Automated Inductive Thematic Analysis
topic Computation and Language
url https://arxiv.org/abs/2509.17167