conftrace_

data contamination

69 papers

Explore in graph

Co-occurring keywords

large language model (13587) benchmark evaluation (1556) evaluation benchmark (257) language model (4599) dynamic evaluation (17) model evaluation (445) code generation (746) membership inference (114) contamination detection (7) llm evaluation (141)

Papers

C2LEVA: Toward Comprehensive and Contamination-Free Language Model Evaluation ACL 2025
User Behavior Prediction as a Generic, Robust, Scalable, and Low-Cost Evaluation Strategy for Estimating Generalization in LLMs ACL 2025
DynaCode: A Dynamic Complexity-Aware Code Benchmark for Evaluating Large Language Models in Code Generation ACL 2025
LNE-Blocking: An Efficient Framework for Contamination Mitigation Evaluation on Large Language Models EMNLP 2025
BALSAM: A Platform for Benchmarking Arabic Large Language Models EMNLP 2025
AntiLeakBench: Preventing Data Contamination by Automatically Constructing Benchmarks with Updated Real-World Knowledge ACL 2025
UnSeenTimeQA: Time-Sensitive Question-Answering Beyond LLMs’ Memorization ACL 2025
LLM-as-an-Interviewer: Beyond Static Testing Through Dynamic LLM Evaluation ACL 2025
Competition-Level Problems are Effective LLM Evaluators ACL 2024
Data Contamination Calibration for Black-box LLMs ACL 2024
MathPile: A Billion-Token-Scale Pretraining Corpus for Math NIPS 2024
MEGAVERSE: Benchmarking Large Language Models Across Languages, Modalities, Models and Tasks NAACL 2024
Investigating Data Contamination in Modern Benchmarks for Large Language Models NAACL 2024
ConStat: Performance-Based Contamination Detection in Large Language Models NIPS 2024
StructEval: Deepen and Broaden Large Language Model Assessment via Structured Evaluation ACL 2024
Confounders in Instance Variation for the Analysis of Data Contamination ACL 2024
A Taxonomy for Data Contamination in Large Language Models ACL 2024
Data Contamination Can Cross Language Barriers EMNLP 2024
FreeEval: A Modular Framework for Trustworthy and Efficient Evaluation of Large Language Models EMNLP 2024
An Open-Source Data Contamination Report for Large Language Models EMNLP 2024
Language Models are Surprisingly Fragile to Drug Names in Biomedical Benchmarks EMNLP 2024
On Leakage of Code Generation Evaluation Datasets EMNLP 2024
VarBench: Robust Language Model Benchmarking Through Dynamic Variable Perturbation EMNLP 2024
CLEAN–EVAL: Clean Evaluation on Contaminated Large Language Models NAACL 2024
Leak, Cheat, Repeat: Data Contamination and Evaluation Malpractices in Closed-Source LLMs EACL 2024