To the Cutoff... and Beyond? A Longitudinal Perspective on LLM Data Contamination

By Manley Roberts, Himanshu Thakur, Christine Herlihy, Colin White, Samuel Dooley. 2024

Subfields: Large Language Models, Evaluation & Benchmarks

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Large Language Models

1. Micah Goldblum
2. Yann LeCun

In Evaluation & Benchmarks

1. Ravid Shwartz-Ziv
2. Yann LeCun
3. Colin White
4. Willie Neiswanger
5. Yarin Gal
6. Nicolas Papernot
7. David Lopez-Paz
8. Patrick Drew McDaniel

Citations in the corpus

• LiveBench: A Challenging, Contamination-Free LLM Benchmark (2024, background): “If the LLM has seen the questions of a benchmark during training, its performance on that benchmark will be artificially inflated [15, 17, 24, 47], hence making many LLM benchmarks unreliable.”