Work

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

Year: 2024
Type: conference-paper
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.
Authors: Kyle Moore, Jesse Roberts, Thao Pham, Oseremhen Ewaleifoh, Douglas Fisher
Language: English
Open Access status: hybrid
OpenAlex ID: W4404781978
FWCI: 0.607
Cites: 18
Cited by: 7
Related to: 10