Improving Steering and Verification in AI-Assisted Data Analysis with Interactive Task Decomposition

Human-LLM CollaborationExplainable AI (XAI)Interactive Data VisualizationSoftware Engineers & DevelopersData Scientists & AnalystsAI/ML Researchers & Engineers

LLM-powered tools like ChatGPT Data Analysis, have the potential to help users tackle the challenging task of data analysis programming, which requires expertise in data processing, programming, and statistics. However, our formative study (n=15) uncovered serious challenges in verifying AI-generated results and steering the AI (i.e., guiding the AI system to produce the desired output). We developed two contrasting approaches to address these challenges. The first (Stepwise) decomposes the problem into step-by-step subgoals with pairs of editable assumptions and code until task completion, while the second (Phasewise) decomposes the entire problem into three editable, logical phases: structured input/output assumptions, execution plan, and code. A controlled, within-subjects experiment (n=18) compared these systems against a conversational baseline. Users reported significantly greater control with the Stepwise and Phasewise systems, and found intervention, correction, and verification easier, compared to the baseline. The results suggest design guidelines and trade-offs for AI-assisted data analysis tools.

Quick Actions

Share

Share this page

ios_share

https://hci.top/en/papers/uist/170918/2024

AdRecommended

Learn AI Coding at CodeNow

open_in_newOpen DOI Link
DOI: https://doi.org/10.1145/3654777.3676345
At a Glance

Paper Snapshot

fact_check
dataset
Source
UIST
calendar_month
Year
2024
emoji_events
Award
No award tagged
group
Authors
7 authors
sell
Subtopics
Human-LLM Collaboration, Explainable AI (XAI), Interactive Data Visualization
work
Professions
Software Engineers & Developers, Data Scientists & Analysts, AI/ML Researchers & Engineers
article
Content Status
Abstract only
hub
Related Papers
10 related papers