mlsanityData to 14 Oct 2026

"The Diagram is like Guardrails": Structuring GenAI-assisted Hypotheses Exploration with an Interactive Shared Representation

arXiv 2503.16791 ↗First posted 21 Mar 2025cs.HC cs.AIcited by 4

Not on the map. Why?

Abstract (arXiv)

Data analysis encompasses a spectrum of tasks, from high-level conceptual reasoning to lower-level execution. While AI-powered tools increasingly support execution tasks, there remains a need for intelligent assistance in conceptual tasks. This paper investigates the design of an ordered node-link tree interface augmented with AI-generated information hints and visualizations, as a potential shared representation for hypothesis exploration. Through a design probe (n=22), participants generated diagrams averaging 21.82 hypotheses. Our findings showed that the node-link diagram acts as "guardrails" for hypothesis exploration, facilitating structured workflows, providing comprehensive overviews, and enabling efficient backtracking. The AI-generated information hints, particularly visualizations, aided users in transforming abstract ideas into data-backed concepts while reducing cognitive load. We further discuss how node-link diagrams can support both parallel exploration and iterative refinement in hypothesis formulation, potentially enhancing the breadth and depth of human-AI collaborative data analysis.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 25 of its 56 references that are in the map. First posted on arXiv 21 Mar 2025.

Builds on

25 of 56 references.

References · 25

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  2. 2024Can LLMs Generate Novel Research Ideas? A Large-Scale Human Study with 100+ NLP Researcherscited by 363
  3. 2024Large Concept Models: Language Modeling in a Sentence Representation Spacecited by 89
  4. 2024A Design Space for Intelligent and Interactive Writing Assistantscited by 76
  5. 2024Hypothesis Generation with Large Language Modelscited by 71
  6. 2023Graphologue: Exploring Large Language Model Responses with Interactive Diagramscited by 66
  7. 2024LLMs Assist NLP Researchers: Critique Paper (Meta-)Reviewingcited by 62
  8. 2024WaitGPT: Monitoring and Steering Conversational LLM Agent in Data Analysis with On-the-Fly Code Visualizationcited by 39
  9. 2024DynaVis: Dynamically Synthesized UI Widgets for Visualization Editingcited by 37
  10. 2024Improving Steering and Verification in AI-Assisted Data Analysis with Interactive Task Decompositioncited by 29
  11. 2023How Do Data Analysts Respond to AI Assistance? A Wizard-of-Oz Studycited by 24
  12. 2022Telling Stories from Computational Notebooks: AI-Assisted Presentation Slides Creation for Presenting Data Science Workcited by 15
13 more
  1. 2024Automating psychological hypothesis generation with AI: when large language models meet causal graphcited by 15
  2. 2023Harnessing the Power of LLMs: Evaluating Human-AI Text Co-Creation through the Lens of News Headline Generationcited by 14
  3. 2021Hypothesis Formalization: Empirical Findings, Software Limitations, and Design Implicationscited by 7
  4. 2024Sketch Then Generate: Providing Incremental User Feedback and Guiding LLM Code Generation through Language-Oriented Code Sketchescited by 7
  5. 2023CrossData: Leveraging Text-Data Connections for Authoring Data Documentscited by 6
  6. 2024Do You See What I See? A Qualitative Study Eliciting High-Level Visualization Comprehensioncited by 5
  7. 2022Understanding and Supporting Debugging Workflows in Multiverse Analysiscited by 3
  8. 2024Advancing GUI for Generative AI: Charting the Design Space of Human-AI Interactions through Task Creativity and Complexitycited by 3
  9. 2024Formulating or Fixating: Effects of Examples on Problem Solving Vary as a Function of Example Presentation Interface Designcited by 3
  10. 2024Towards Intent-based User Interfaces: Charting the Design Space of Intent-AI Interactions Across Task Typescited by 3
  11. 2024Frontend Diffusion: Exploring Intent-Based User Interfaces through Abstract-to-Detailed Task Transitionscited by 3
  12. 2024Intelligent Canvas: Enabling Design-Like Exploratory Visual Data Analysis with Generative AI through Rapid Prototyping, Iteration and Curationcited by 2
  13. 2022Recommendations for Visualization Recommendations: Exploring Preferences and Priorities in Public Healthcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 3.

4 papers.

  1. 2026Alignment-Process-Outcome: Rethinking How AIs and Humans Collaboratecited by 1
  2. 2025ChatGraPhT: A Visual Conversation Interface for Multi-Path Reflection with Agentic LLM Supportcited by 0
  3. 2026AdaLens: Interactive Storyline for Monitoring and Steering Long-Running Agentic Data Analysiscited by 0
  4. 2026Asterism: Exploring and Synthesizing Scattered Observations into Literature-Grounded Hypotheses and Theoriescited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Visualizing Thought: Conceptual Diagrams Enable Robust Planning in LMMs
  2. 2025Interactive Reasoning: Visualizing and Controlling Chain-of-Thought Reasoning in Large Language Models
  3. 2025HypoChainer: A Collaborative System Combining LLMs and Knowledge Graphs for Hypothesis-Driven Scientific Discovery
  4. 2025Draw with Thought: Unleashing Multimodal Reasoning for Scientific Diagram Generation
  5. 2025In-situ graph reasoning and knowledge expansion using Graph-PReFLexOR
  6. 2026HiLSVA: Design and Evaluation of a Human-in-the-Loop Agentic System for Scientific Visualization
  7. 2026Intentmaking and Sensemaking: Human Interaction with AI-Guided Mathematical Discovery
  8. 2026Higher-Order Knowledge Representations for Agentic Scientific Reasoning