# Bridging Human Interpretation and Machine Representation: A Landscape of Qualitative Data Analysis in the LLM Era

arXiv: https://arxiv.org/abs/2601.11739 · HTML: https://mlsanity.com/paper/2601.11739/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 28 of its 166 references that are in the map.
- First posted on arXiv 16 Jan 2026.

## Builds on (most cited first, 28 of 28)

- [A large annotated corpus for learning natural language inference](https://mlsanity.com/paper/1508.05326/) (2015)
- [From Local to Global: A Graph RAG Approach to Query-Focused Summarization](https://mlsanity.com/paper/2404.16130/) (2024)
- [ChatDev: Communicative Agents for Software Development](https://mlsanity.com/paper/2307.07924/) (2023)
- [Why Do Multi-Agent LLM Systems Fail?](https://mlsanity.com/paper/2503.13657/) (2025)
- [A Survey on Deep Learning for Named Entity Recognition](https://mlsanity.com/paper/1812.09449/) (2018)
- [Grounded Copilot: How Programmers Interact with Code-Generating Models](https://mlsanity.com/paper/2206.15000/) (2022)
- [Concept Induction: Analyzing Unstructured Text with High-Level Concepts Using LLooM](https://mlsanity.com/paper/2404.12259/) (2024)
- [LLM-in-the-loop: Leveraging Large Language Model for Thematic Analysis](https://mlsanity.com/paper/2310.15100/) (2023)
- [The Future is not One-dimensional: Complex Event Schema Induction by Graph Modeling for Event Prediction](https://mlsanity.com/paper/2104.06344/) (2021)
- [A Review on Fact Extraction and Verification](https://mlsanity.com/paper/2010.03001/) (2020)
- [CoAIcoder: Examining the Effectiveness of AI-assisted Human-to-Human Collaboration in Qualitative Analysis](https://mlsanity.com/paper/2304.05560/) (2023)
- [Large Language Models in Qualitative Research: Uses, Tensions, and Intentions](https://mlsanity.com/paper/2410.07362/) (2024)
- [Professional Software Developers Don't Vibe, They Control: AI Agent Use for Coding in 2025](https://mlsanity.com/paper/2512.14012/) (2025)
- [Open-Domain Hierarchical Event Schema Induction by Incremental Prompting and Verification](https://mlsanity.com/paper/2307.01972/) (2023)
- [HICode: Hierarchical Inductive Coding with LLMs](https://mlsanity.com/paper/2509.17946/) (2025)
- [Automating Thematic Analysis: How LLMs Analyse Controversial Topics](https://mlsanity.com/paper/2405.06919/) (2024)
- [Identifying civilians killed by police with distantly supervised entity-event extraction](https://mlsanity.com/paper/1707.07086/) (2017)
- [Auto-TA: Towards Scalable Automated Thematic Analysis (TA) via Multi-Agent Large Language Models with Reinforcement Learning](https://mlsanity.com/paper/2506.23998/) (2025)
- [QuaLLM: An LLM-based Framework to Extract Quantitative Insights from Online Forums](https://mlsanity.com/paper/2405.05345/) (2024)
- [LOGOS: LLM-driven End-to-End Grounded Theory Development and Schema Induction for Qualitative Research](https://mlsanity.com/paper/2509.24294/) (2025)
- [Intent-Aware Schema Generation And Refinement For Literature Review Tables](https://mlsanity.com/paper/2507.19521/) (2025)
- [DeTAILS: Deep Thematic Analysis with Iterative LLM Support](https://mlsanity.com/paper/2510.17575/) (2025)
- [Large Language Models in Thematic Analysis: Prompt Engineering, Evaluation, and Guidelines for Qualitative Software Engineering Research](https://mlsanity.com/paper/2510.18456/) (2025)
- [PolicyPulse: LLM-Synthesis Tool for Policy Researchers](https://mlsanity.com/paper/2505.23994/) (2025)
- [Text Annotation via Inductive Coding: Comparing Human Experts to LLMs in Qualitative Data Analysis](https://mlsanity.com/paper/2512.00046/) (2025)
- [Optimizing Generative AI's Accuracy and Transparency in Inductive Thematic Analysis: A Human-AI Comparison](https://mlsanity.com/paper/2503.16485/) (2025)
- [SFT-TA: Supervised Fine-Tuned Agents in Multi-Agent LLMs for Automated Inductive Thematic Analysis](https://mlsanity.com/paper/2509.17167/) (2025)
- [Qualitative Data Analysis in Software Engineering: Techniques and Teaching Insights](https://mlsanity.com/paper/2406.08228/) (2024)

## Abstract (arXiv)

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 4×4 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.