Questionable practices in machine learning
This addresses the problem of unreliable evaluation and reproducibility in ML research, particularly for LLMs, which is incremental as it catalogues existing issues rather than proposing new solutions.
The paper identifies 44 questionable research practices in machine learning that can undermine reported results, with a focus on evaluating large language models on public benchmarks, and also discusses irreproducible research practices.
Evaluating modern ML models is hard. The strong incentive for researchers and companies to report a state-of-the-art result on some metric often leads to questionable research practices (QRPs): bad practices which fall short of outright research fraud. We describe 44 such practices which can undermine reported results, giving examples where possible. Our list emphasises the evaluation of large language models (LLMs) on public benchmarks. We also discuss "irreproducible research practices", i.e. decisions that make it difficult or impossible for other researchers to reproduce, build on or audit previous research.