Work

Leak, Cheat, Repeat: Data Contamination and Evaluation Malpractices in Closed-Source LLMs

Year: 2024

Type: conference-paper

Abstract: Simone Balloccu, Patrícia Schmidtová, Mateusz Lango, Ondrej Dusek. Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.

Source: Conference of the European Chapter of the Association for Computational Linguistics

DOI: 10.18653/v1/2024.eacl-long.5

Authors: Simone Balloccu, Patrícia Schmidtová, Mateusz Lango, Ondrej Dusek

Institution: Charles University

Language: English

Topic: Topic Modeling

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

Funders: Univerzita Karlova v Praze, HORIZON EUROPE European Research Council

Award: Next-Generation Natural Language Generation

OpenAlex ID: W4411630291

FWCI: 20.26

Cites:

Cited by: 69

Related to: 10