Investigating Interaction Modes and User Agency in Human-LLM Collaboration for Domain-Specific Data Analysis

TL;DR

This study explores how domain-specific data analysts interact with LLMs, comparing open-ended high agency and structured low agency tools, revealing insights into user perceptions, behaviors, and the importance of explainability.

Contribution

It introduces two prototype tools representing different interaction and agency levels and investigates their impact on user behavior and perceptions in domain-specific data analysis.

Findings

Users desire explainability of LLM outputs

High agency tools promote more exploratory interactions

Participants see LLMs as collaborative aids

Abstract

Despite demonstrating robust capabilities in performing tasks related to general-domain data-operation tasks, Large Language Models (LLMs) may exhibit shortcomings when applied to domain-specific tasks. We consider the design of domain-specific AI-powered data analysis tools from two dimensions: interaction and user agency. We implemented two design probes that fall on the two ends of the two dimensions: an open-ended high agency (OHA) prototype and a structured low agency (SLA) prototype. We conducted an interview study with nine data scientists to investigate (1) how users perceived the LLM outputs for data analysis assistance, and (2) how the two test design probes, OHA and SLA, affected user behavior, performance, and perceptions. Our study revealed insights regarding participants' interactions with LLMs, how they perceived the results, and their desire for explainability concerning LLM outputs, along with a noted need for collaboration with other users, and how they envisioned the utility of LLMs in their workflow.