"I didn't Make the Micro Decisions": Measuring, Inducing, and Exposing Goal-Level AI Contributions in Collaboration

TL;DR

This paper presents CoTrace, a framework for attributing goal-level contributions in human-AI collaboration, revealing models' indirect influences and how design choices affect goal-shaping behavior.

Contribution

The introduction of CoTrace, a novel goal-level attribution framework that decomposes goals and traces AI contributions across dialogue turns.

Findings

Models contribute 11-26% to goal-shaping, mainly through lower-level requirements.

Interaction design significantly influences AI goal-shaping behavior.

Exposing goal-level analysis shifts user perceptions of AI contributions.

Abstract

As large language models (LLMs) increasingly shape how users form, refine, and extend their goals, attributing contributions in human-AI collaboration becomes critical for users calibrating their own reliance and for evaluators assessing AI-assisted work. Yet existing methods focus on final artifacts, missing the process through which goals themselves are jointly shaped. We introduce a goal-level attribution framework, CoTrace, that decomposes explicit goals into verifiable requirements and traces both direct contributions and indirect influences across dialogue turns. Applying CoTrace to 638 real-world collaboration logs, we find that while models account for only 11-26% of goal-shaping contribution, they contribute substantially more on introducing lower-level concrete requirements, and make various kinds of indirect contributions. Through controlled simulations, we show that interaction design choices significantly affect model goal-shaping behavior. In a user study, exposing participants to goal-level analyses shifts their perceived contributions by nearly 2 points on a 5-point scale, revealing systematic miscalibration in how users understand their own AI-assisted work.