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

arXiv: https://arxiv.org/abs/2503.16791 · HTML: https://mlsanity.com/paper/2503.16791/

## 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 (most cited first, 25 of 25)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Can LLMs Generate Novel Research Ideas? A Large-Scale Human Study with 100+ NLP Researchers](https://mlsanity.com/paper/2409.04109/) (2024)
- [Large Concept Models: Language Modeling in a Sentence Representation Space](https://mlsanity.com/paper/2412.08821/) (2024)
- [A Design Space for Intelligent and Interactive Writing Assistants](https://mlsanity.com/paper/2403.14117/) (2024)
- [Hypothesis Generation with Large Language Models](https://mlsanity.com/paper/2404.04326/) (2024)
- [Graphologue: Exploring Large Language Model Responses with Interactive Diagrams](https://mlsanity.com/paper/2305.11473/) (2023)
- [LLMs Assist NLP Researchers: Critique Paper (Meta-)Reviewing](https://mlsanity.com/paper/2406.16253/) (2024)
- [WaitGPT: Monitoring and Steering Conversational LLM Agent in Data Analysis with On-the-Fly Code Visualization](https://mlsanity.com/paper/2408.01703/) (2024)
- [DynaVis: Dynamically Synthesized UI Widgets for Visualization Editing](https://mlsanity.com/paper/2401.10880/) (2024)
- [Improving Steering and Verification in AI-Assisted Data Analysis with Interactive Task Decomposition](https://mlsanity.com/paper/2407.02651/) (2024)
- [How Do Data Analysts Respond to AI Assistance? A Wizard-of-Oz Study](https://mlsanity.com/paper/2309.10108/) (2023)
- [Telling Stories from Computational Notebooks: AI-Assisted Presentation Slides Creation for Presenting Data Science Work](https://mlsanity.com/paper/2203.11085/) (2022)
- [Automating psychological hypothesis generation with AI: when large language models meet causal graph](https://mlsanity.com/paper/2402.14424/) (2024)
- [Harnessing the Power of LLMs: Evaluating Human-AI Text Co-Creation through the Lens of News Headline Generation](https://mlsanity.com/paper/2310.10706/) (2023)
- [Hypothesis Formalization: Empirical Findings, Software Limitations, and Design Implications](https://mlsanity.com/paper/2104.02712/) (2021)
- [Sketch Then Generate: Providing Incremental User Feedback and Guiding LLM Code Generation through Language-Oriented Code Sketches](https://mlsanity.com/paper/2405.03998/) (2024)
- [CrossData: Leveraging Text-Data Connections for Authoring Data Documents](https://mlsanity.com/paper/2310.11639/) (2023)
- [Do You See What I See? A Qualitative Study Eliciting High-Level Visualization Comprehension](https://mlsanity.com/paper/2402.15605/) (2024)
- [Understanding and Supporting Debugging Workflows in Multiverse Analysis](https://mlsanity.com/paper/2210.03804/) (2022)
- [Advancing GUI for Generative AI: Charting the Design Space of Human-AI Interactions through Task Creativity and Complexity](https://mlsanity.com/paper/2401.02494/) (2024)
- [Formulating or Fixating: Effects of Examples on Problem Solving Vary as a Function of Example Presentation Interface Design](https://mlsanity.com/paper/2401.11022/) (2024)
- [Towards Intent-based User Interfaces: Charting the Design Space of Intent-AI Interactions Across Task Types](https://mlsanity.com/paper/2404.18196/) (2024)
- [Frontend Diffusion: Exploring Intent-Based User Interfaces through Abstract-to-Detailed Task Transitions](https://mlsanity.com/paper/2408.00778/) (2024)
- [Intelligent Canvas: Enabling Design-Like Exploratory Visual Data Analysis with Generative AI through Rapid Prototyping, Iteration and Curation](https://mlsanity.com/paper/2402.08812/) (2024)
- [Recommendations for Visualization Recommendations: Exploring Preferences and Priorities in Public Health](https://mlsanity.com/paper/2202.01335/) (2022)

## Built on by (most cited first, 4 of 4)

- [Alignment-Process-Outcome: Rethinking How AIs and Humans Collaborate](https://mlsanity.com/paper/2603.08017/) (2026)
- [ChatGraPhT: A Visual Conversation Interface for Multi-Path Reflection with Agentic LLM Support](https://mlsanity.com/paper/2512.22790/) (2025)
- [AdaLens: Interactive Storyline for Monitoring and Steering Long-Running Agentic Data Analysis](https://mlsanity.com/paper/2608.17834/) (2026)
- [Asterism: Exploring and Synthesizing Scattered Observations into Literature-Grounded Hypotheses and Theories](https://mlsanity.com/paper/2610.02673/) (2026)

## 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.