Saved in:
Bibliographic Details
Main Authors: Pi, Xinyu, Yang, Qisen, Nguyen, Chuong, Shen, Hua
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2601.11739
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918293666791424
author Pi, Xinyu
Yang, Qisen
Nguyen, Chuong
Shen, Hua
author_facet Pi, Xinyu
Yang, Qisen
Nguyen, Chuong
Shen, Hua
contents LLMs are increasingly used to support qualitative research, yet existing systems produce outputs that vary widely--from trace-faithful summaries to theory-mediated explanations and system models. To make these differences explicit, we introduce a 4$\times$4 landscape crossing four levels of meaning-making (descriptive, categorical, interpretive, theoretical) with four levels of modeling (static structure, stages/timelines, causal pathways, feedback dynamics). Applying the landscape to prior LLM-based automation highlights a strong skew toward low-level meaning and low-commitment representations, with few reliable attempts at interpretive/theoretical inference or dynamical modeling. Based on the revealed gap, we outline an agenda for applying and building LLM-systems that make their interpretive and modeling commitments explicit, selectable, and governable.
format Preprint
id arxiv_https___arxiv_org_abs_2601_11739
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Bridging Human Interpretation and Machine Representation: A Landscape of Qualitative Data Analysis in the LLM Era
Pi, Xinyu
Yang, Qisen
Nguyen, Chuong
Shen, Hua
Computation and Language
LLMs are increasingly used to support qualitative research, yet existing systems produce outputs that vary widely--from trace-faithful summaries to theory-mediated explanations and system models. To make these differences explicit, we introduce a 4$\times$4 landscape crossing four levels of meaning-making (descriptive, categorical, interpretive, theoretical) with four levels of modeling (static structure, stages/timelines, causal pathways, feedback dynamics). Applying the landscape to prior LLM-based automation highlights a strong skew toward low-level meaning and low-commitment representations, with few reliable attempts at interpretive/theoretical inference or dynamical modeling. Based on the revealed gap, we outline an agenda for applying and building LLM-systems that make their interpretive and modeling commitments explicit, selectable, and governable.
title Bridging Human Interpretation and Machine Representation: A Landscape of Qualitative Data Analysis in the LLM Era
topic Computation and Language
url https://arxiv.org/abs/2601.11739