Position: Language model developers should report train-test overlap

Andy K. Zhang, Kevin Klyman, Yifan Mai, Yoav Levine, Yian Zhang +2 more
2/14/2026

No confident code implementation found for this paper. 2 possible matches can be shown below.

Semantic Scholar

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. 2 weaker matches are hidden by default — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

No Free Delivery Service: Epistemic limits of passive data collection in complex social systems

70% match2026

Beyond Accuracy: An Empirical Study on Unit Testing in Open-source Deep Learning Projects

67% match2024

Loss-to-Loss Prediction: Scaling Laws for All Datasets

67% match2 repos42024

Cumulative Consensus Score: Label-Free and Model-Agnostic Evaluation of Object Detectors in Deployment

67% match2025

Reshuffling Resampling Splits Can Improve Generalization of Hyperparameter Optimization

67% match1 repo12026

ODD: Overlap-aware Estimation of Model Performance under Distribution Shift

67% match2025

Cite this paper

@article{zhang2026position,
  title  = {Position: Language model developers should report train-test overlap},
  author = {Andy K. Zhang and Kevin Klyman and Yifan Mai and Yoav Levine and Yian Zhang and Rishi Bommasani and Percy Liang},
  year   = {2026},
  url    = {https://api.semanticscholar.org/CorpusID:4c8399cb5447c12c1b489459e2db5a51723baa56},
  journal = {ICML 2025 2025}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/4c8399cb5447c12c1b489459e2db5a51723baa56.svg)](https://codeofpaper.com/paper/4c8399cb5447c12c1b489459e2db5a51723baa56)

Discussion