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

arXiv: https://arxiv.org/abs/2605.21363 · HTML: https://mlsanity.com/paper/2605.21363/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 32 references that are in the map.
- First posted on arXiv 20 May 2026.

## Builds on (most cited first, 19 of 19)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [InFoBench: Evaluating Instruction Following Ability in Large Language Models](https://mlsanity.com/paper/2401.03601/) (2024)
- [Checklists Are Better Than Reward Models For Aligning Language Models](https://mlsanity.com/paper/2507.18624/) (2025)
- [Collaborative Gym: A Framework for Enabling and Evaluating Human-Agent Collaboration](https://mlsanity.com/paper/2412.15701/) (2024)
- [Stylometric Detection of AI-Generated Text in Twitter Timelines](https://mlsanity.com/paper/2303.03697/) (2023)
- [Mind the Sim2Real Gap in User Simulation for Agentic Tasks](https://mlsanity.com/paper/2603.11245/) (2026)
- [Levels of Autonomy for AI Agents](https://mlsanity.com/paper/2506.12469/) (2025)
- [Future of Work with AI Agents: Auditing Automation and Augmentation Potential across the U.S. Workforce](https://mlsanity.com/paper/2506.06576/) (2025)
- [Evaluating Human-AI Collaboration: A Review and Methodological Framework](https://mlsanity.com/paper/2407.19098/) (2024)
- [Watermarking Techniques for Large Language Models: A Survey](https://mlsanity.com/paper/2409.00089/) (2024)
- [Taxonomy of User Needs and Actions](https://mlsanity.com/paper/2510.06124/) (2025)
- [ShareChat: A Dataset of Chatbot Conversations in the Wild](https://mlsanity.com/paper/2512.17843/) (2025)
- [Which Contributions Deserve Credit? Perceptions of Attribution in Human-AI Co-Creation](https://mlsanity.com/paper/2502.18357/) (2025)
- [The StudyChat Dataset: Analyzing Student Dialogues With ChatGPT in an Artificial Intelligence Course](https://mlsanity.com/paper/2503.07928/) (2025)
- [DraftMarks: Enhancing Transparency in Human-AI Co-Writing Through Interactive Skeuomorphic Process Traces](https://mlsanity.com/paper/2509.23505/) (2025)
- [Completion neq Collaboration: Scaling Collaborative Effort with Agents](https://mlsanity.com/paper/2510.25744/) (2025)
- [DiscoverLLM: From Executing Intents to Discovering Them](https://mlsanity.com/paper/2602.03429/) (2026)
- [Open-Ended Goal Inference through Actions and Language for Human-Robot Collaboration](https://mlsanity.com/paper/2512.04453/) (2025)
- [How2Everything: Mining the Web for How-To Procedures to Evaluate and Improve LLMs](https://mlsanity.com/paper/2602.08808/) (2026)

## Built on by (most cited first, 1 of 1)

- [Value Over Language Model: Detecting Original Contribution in Writing](https://mlsanity.com/paper/2609.00700/) (2026)

## Abstract (arXiv)

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.