New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

autodetect dataset contamination #1636

Open

KennethEnevoldsen opened this issue Dec 27, 2024 · 0 comments

Labels

Contributor

KennethEnevoldsen commented Dec 27, 2024 •

edited

Loading

In multiple threads tracking dataset contamination have been mentioned as multiple models do not share their training dataset.

This issue is intended to link these discussions together as well as potential approaches to go about this issue.

LLM specific (probably won't work for embeddings)
- Time Travel in LLMs: Tracing Data Contamination in Large Language Models (ref)
Overview
- Leak, Cheat, Repeat: Data Contamination
  and Evaluation Malpractices in Closed-Source LLMs (ref)
related work
- LM Contamination Index

(did a social media post asking for methods here as well)

KennethEnevoldsen added the leaderboard label

KennethEnevoldsen changed the title ~~track and detect dataset contamination~~ autodetect dataset contamination

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment