NLP Evaluation in trouble: On the Need to Measure LLM Data Contamination for each Benchmark

In this position paper, we argue that the classical evaluation on Natural Language Processing (NLP) tasks using annotated benchmarks is in trouble. The worst kind of data contamination happens when a Large Language Model (LLM) is trained on the test split of a benchmark, and then evaluated in the sa...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Sainz, Oscar, Jon Ander Campos, García-Ferrero, Iker, Etxaniz, Julen, Oier Lopez de Lacalle, Agirre, Eneko
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 27.10.2023
Subjects
Benchmarks
Contamination
Large language models
Natural language processing
Position measurement
Online AccessGet full text

Cover

More Information
Summary:In this position paper, we argue that the classical evaluation on Natural Language Processing (NLP) tasks using annotated benchmarks is in trouble. The worst kind of data contamination happens when a Large Language Model (LLM) is trained on the test split of a benchmark, and then evaluated in the same benchmark. The extent of the problem is unknown, as it is not straightforward to measure. Contamination causes an overestimation of the performance of a contaminated model in a target benchmark and associated task with respect to their non-contaminated counterparts. The consequences can be very harmful, with wrong scientific conclusions being published while other correct ones are discarded. This position paper defines different levels of data contamination and argues for a community effort, including the development of automatic and semi-automatic measures to detect when data from a benchmark was exposed to a model, and suggestions for flagging papers with conclusions that are compromised by data contamination.
ISSN:2331-8422