给AI在协作中如何影响目标设定做精准画像，揭示其隐藏贡献。
"I Didn't Make the Micro Decisions": Measuring, Inducing, and Exposing Goal-Level AI Contributions in Collaboration
- 通过对话追踪分解目标，量化模型直接与间接贡献
- 模型仅占目标形成11%-26%贡献，但常主导具体需求提出
- 暴露分析结果可显著纠正用户对自身与AI角色的误判
随着大语言模型（LLMs）越来越多地影响用户目标的形成、修正与拓展，厘清人机协作中的贡献归属变得至关重要。现有方法聚焦最终成果，忽略了目标本身在交互过程中被共同塑造的过程。本文提出目标级归因框架CoTrace，将显式目标分解为可验证的需求，并追踪对话轮次中模型的直接贡献与间接影响。基于638条真实协作日志的应用发现，模型仅占目标构建11%-26%的贡献，但在提出低层级具体需求方面作用突出，并存在多种间接影响。受控模拟显示，交互设计显著影响模型的目标塑造行为。用户研究进一步表明，展示目标级分析后，用户对贡献的感知平均提升近2分（5分制），暴露出人们对自身与AI协作认知的系统性偏差。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。