mlsanityData to 14 Oct 2026

Prompting Datasets: Data Discovery with Conversational Agents

arXiv 2312.09947 ↗First posted 15 Dec 2023cs.HCcited by 1

On the map: LLM agents and tool use → Web, search, and research agents

Abstract (arXiv)

Can large language models assist in data discovery? Data discovery predominantly happens via search on a data portal or the web, followed by assessment of the dataset to ensure it is fit for the intended purpose. The ability of conversational generative AI (CGAI) to support recommendations with reasoning implies it can suggest datasets to users, explain why it has done so, and provide information akin to documentation regarding the dataset in order to support a use decision. We hold 3 workshops with data users and find that, despite limitations around web capabilities, CGAIs are able to suggest relevant datasets and provide many of the required sensemaking activities, as well as support dataset analysis and manipulation. However, CGAIs may also suggest fictional datasets, and perform inaccurate analysis. We identify emerging practices in data discovery and present a model of these to inform future research directions and data prompt design.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use. Builds on 17 of its 48 references that are in the map. First posted on arXiv 15 Dec 2023.

Builds on

17 of 48 references.

References · 17

  1. 2019Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AIcited by 1,552
  2. 2023ChatGPT Outperforms Crowd-Workers for Text-Annotation Taskscited by 870
  3. 2023A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPTcited by 619
  4. 2023Augmented Language Models: a Surveycited by 403
  5. 2023ChatIE: Zero-Shot Information Extraction via Chatting with ChatGPTcited by 250
  6. 2017Challenges in Data-to-Document Generationcited by 226
  7. 2023In-Context Impersonation Reveals Large Language Models' Strengths and Biasescited by 155
  8. 2023GeneGPT: Augmenting Large Language Models with Domain Tools for Improved Access to Biomedical Informationcited by 117
  9. 2023Can we trust the evaluation on ChatGPT?cited by 63
  10. 2019Dataset search: a surveycited by 36
  11. 2021Principles of Explanation in Human-AI Systemscited by 25
  12. 2023A Prompt Log Analysis of Text-to-Image Generation Systemscited by 24
5 more
  1. 2023Investigating Conversational Search Behavior For Domain Explorationcited by 9
  2. 2019Talking datasets: Understanding data sensemaking behaviourscited by 7
  3. 2018Everything you always wanted to know about a dataset: studies in data summarisationcited by 4
  4. 2023Learnings from Data Integration for Augmented Language Modelscited by 4
  5. 2020Conversational Browsingcited by 2

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025DatasetResearch: Benchmarking Agent Systems for Demand-Driven Dataset Discoverycited by 9

Similar, not cited

Close in wording, no citation either way

  1. 2025ConDABench: Interactive Evaluation of Language Models for Data Analysis
  2. 2023DataChat: Prototyping a Conversational Agent for Dataset Search and Visualization
  3. 2024ConvoSense: Overcoming Monotonous Commonsense Inferences for Conversational AI
  4. 2024DataAgent: Evaluating Large Language Models' Ability to Answer Zero-Shot, Natural Language Queries
  5. 2022Evaluation of Synthetic Datasets for Conversational Recommender Systems
  6. 2024Generative AI for Synthetic Data Generation: Methods, Challenges and the Future
  7. 2024Better Synthetic Data by Retrieving and Transforming Existing Datasets
  8. 2024Into the Unknown Unknowns: Engaged Human Learning through Participation in Language Model Agent Conversations