TurnStyle: A Framework for Analyzing Human Conversational Behaviors to Predict Success in LLM-Assisted Tasks

要旨

LLMs are widespread across educational and professional environments, often used to tackle tasks beyond users' prior expertise. {However, there is limited work on task-agnostic, turn-level frameworks to characterize human communication styles with LLMs that are linked to better task outcomes.} We introduce TurnStyle, a framework that provides a turn-level taxonomy of human contributions in human–AI conversations, grounded in collaborative learning theory, with a reliability protocol and open-source tooling for public datasets. We apply TurnStyle to two public multi-turn corpora with objective outcomes – StudyChat (college-level assignments) and DevGPT (software engineering issues and pull requests (PRs)) – and to a workplace reskilling randomized trial in which management consultants used ChatGPT for coding, statistics, and machine learning. Across 3,365 conversations with 26,335 human turns spanning the three datasets, mixed-effects and sequence analyses converge on task-agnostic, trainable behaviors that predict task success; this has implications for training, evaluation, and the design of collaborative AI systems.

受賞
Honorable Mention
著者
Urvi Awasthi
Boston Consulting Group, New York, New York, United States
Lisa Krayer
Boston Consulting Group, Philadelphia, Pennsylvania, United States
Daniel Sack
Boston Consulting Group, Stockholm, Sweden

会議: CHI 2026

ACM CHI Conference on Human Factors in Computing Systems

セッション: AI in Work and Expertise

P1 - Room 124
7 件の発表
2026-04-13 20:15:00
2026-04-13 21:45:00