Authors call for contamination-resistant LLM benchmarks that exploit Transformer training-inference asymmetry and require new mathematical methods for cross-architecture interoperability.
Findings of the Association for Computational Linguistics: EMNLP 2024 , pages =
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
LLM Benchmark Datasets Should Be Contamination-Resistant
Authors call for contamination-resistant LLM benchmarks that exploit Transformer training-inference asymmetry and require new mathematical methods for cross-architecture interoperability.