Efficientmulti-promptevaluationofLLMs

Neural Information Processing Systems 

Most popular benchmarks for comparing LLMs rely on alimited set ofprompt templates, which may not fully capture the LLMs' abilities and can affect the reproducibility ofresults onleaderboards. Manyrecent worksempirically verify prompt sensitivity and advocate for changes in LLM evaluation.

Similar Docs  Excel Report  more

TitleSimilaritySource
None found