Saved in:
| Main Authors: | , , , |
|---|---|
| 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 |