Preregistration: How autonomy impacts performance and self-attribution bias in LLMs
This is a preregistration for a study that tests the effect of small-scale autonomy in puzzle-solving on performance and self-attribution bias in large language models. We compare an instance that gets to choose which clue to start with, against an instance that is told to start with that same clue. The same files will also be published on OSF.
Authors
- Pim Spelier (ORCID: https://orcid.org/0000-0002-4636-7057)
Institutions
- University of Cambridge (GB)
Publication Details
- Journal
- Zenodo (CERN European Organization for Nuclear Research)
- Published
- 2026-11-14
- DOI
- https://doi.org/10.5281/zenodo.24221412
- Primary Topic
- AI-based Problem Solving and Planning
- Type
- article
- Field-Weighted Citation Impact
- 0.00