conftrace_

benchmark leakage

5 papers

Explore in graph

Co-occurring keywords

benchmark evaluation (1556) data contamination (69) large language model (13587) language model (4599) model evaluation (445) dataset updating (1) large language model evaluation (20) performance inflation (2) multilingual model (925) language model benchmark (9)

Papers

CodeArena: A Collective Evaluation Platform for LLM Code Generation ACL 2025
Automating Dataset Updates Towards Reliable and Timely Evaluation of Large Language Models NIPS 2024
Inference-Time Decontamination: Reusing Leaked Benchmarks for Large Language Model Evaluation EMNLP 2024
VarBench: Robust Language Model Benchmarking Through Dynamic Variable Perturbation EMNLP 2024
Data Contamination Can Cross Language Barriers EMNLP 2024