# Data Therapist: Eliciting Domain Knowledge from Subject Matter Experts Using Large Language Models

arXiv: https://arxiv.org/abs/2505.00455 · HTML: https://mlsanity.com/paper/2505.00455/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 62 references that are in the map.
- First posted on arXiv 1 May 2025.

## Builds on (most cited first, 25 of 25)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Emergent Abilities of Large Language Models](https://mlsanity.com/paper/2206.07682/) (2022)
- [Datasheets for Datasets](https://mlsanity.com/paper/1803.09010/) (2018)
- [PaLM 2 Technical Report](https://mlsanity.com/paper/2305.10403/) (2023)
- [Social Simulacra: Creating Populated Prototypes for Social Computing Systems](https://mlsanity.com/paper/2208.04024/) (2022)
- [Predictability and Surprise in Large Generative Models](https://mlsanity.com/paper/2202.07785/) (2022)
- [Language Models as Knowledge Bases: On Entity Representations, Storage Capacity, and Paraphrased Queries](https://mlsanity.com/paper/2008.09036/) (2020)
- [LIDA: A Tool for Automatic Generation of Grammar-Agnostic Visualizations and Infographics using Large Language Models](https://mlsanity.com/paper/2303.02927/) (2023)
- [ChartGPT: Leveraging LLMs to Generate Charts from Abstract Natural Language](https://mlsanity.com/paper/2311.01920/) (2023)
- [VizML: A Machine Learning Approach to Visualization Recommendation](https://mlsanity.com/paper/1808.04819/) (2018)
- [Data Formulator: AI-powered Concept-driven Visualization Authoring](https://mlsanity.com/paper/2309.10094/) (2023)
- [Let the Chart Spark: Embedding Semantic Context into Chart with Text-to-Image Generative Model](https://mlsanity.com/paper/2304.14630/) (2023)
- [VizLinter: A Linter and Fixer Framework for Data Visualization](https://mlsanity.com/paper/2108.10299/) (2021)
- [Surfacing Visualization Mirages](https://mlsanity.com/paper/2001.02316/) (2020)
- [Table2Charts: Recommending Charts by Learning Shared Table Representations](https://mlsanity.com/paper/2008.11015/) (2020)
- [Data Changes Everything: Challenges and Opportunities in Data Visualization Design Handoff](https://mlsanity.com/paper/1908.00192/) (2019)
- [Effects of Human vs. Automatic Feedback on Students' Understanding of AI Concepts and Programming Style](https://mlsanity.com/paper/2011.10653/) (2020)
- [Vis Ex Machina: An Analysis of Trust in Human versus Algorithmically Generated Visualization Recommendations](https://mlsanity.com/paper/2101.04251/) (2021)
- [Perceptual Pat: A Virtual Human System for Iterative Visualization Design](https://mlsanity.com/paper/2303.06537/) (2023)
- [A User-centered Design Study in Scientific Visualization Targeting Domain Experts](https://mlsanity.com/paper/1903.12349/) (2019)
- [Making the Invisible Visible: Risks and Benefits of Disclosing Metadata in Visualization](https://mlsanity.com/paper/2108.13270/) (2021)
- [Data Hunches: Incorporating Personal Knowledge into Visualizations](https://mlsanity.com/paper/2109.07035/) (2021)

## Abstract (arXiv)

Effective data visualization requires not only technical proficiency but also a deep understanding of the domain-specific context in which data exists. This context often includes tacit knowledge about data provenance, quality, and intended use, which is rarely explicit in the dataset itself. Motivated by growing demands to surface tacit knowledge, we present the Data Therapist, a web-based system that helps domain experts externalize such implicit knowledge through a mixed-initiative process combining iterative Q&A with interactive annotation. Powered by a large language model, the system automatically analyzes user-supplied datasets, prompts users with targeted questions, and supports annotation at varying levels of granularity. The resulting structured knowledge base can inform both human and automated visualization design. A qualitative study with expert pairs from Accounting, Political Science, and Computer Security revealed recurring patterns in how expert reason about their data and highlighted opportunities for AI support to enhance visualization design.