English

The Base-Rate Effect on LLM Benchmark Performance: Disambiguating Test-Taking Strategies from Benchmark Performance

Computation and Language 2024-10-01 v2 Artificial Intelligence

Abstract

Cloze testing is a common method for measuring the behavior of large language models on a number of benchmark tasks. Using the MMLU dataset, we show that the base-rate probability (BRP) differences across answer tokens are significant and affect task performance ie. guess A if uncertain. We find that counterfactual prompting does sufficiently mitigate the BRP effect. The BRP effect is found to have a similar effect to test taking strategies employed by humans leading to the conflation of task performance and test-taking ability. We propose the Nvr-X-MMLU task, a variation of MMLU, which helps to disambiguate test-taking ability from task performance and reports the latter.

Cite

@article{arxiv.2406.11634,
  title  = {The Base-Rate Effect on LLM Benchmark Performance: Disambiguating Test-Taking Strategies from Benchmark Performance},
  author = {Kyle Moore and Jesse Roberts and Thao Pham and Oseremhen Ewaleifoh and Doug Fisher},
  journal= {arXiv preprint arXiv:2406.11634},
  year   = {2024}
}
R2 v1 2026-06-28T17:08:47.709Z