AI Research
Coresets Before Score Sets: Evaluation-Unsupervised Prompt Subset Selection for LLM Benchmarks
We study LLM benchmark coreset selection: selecting a small subset of prompts over multiple benchmarks whose induced model scores and rankings approximate those obtained from the full benchmark suite. In evaluation-unsupervised benchmark coreset selection (our approach), the sele...
AC
ArXiv CS.AI
Source
2 min
ArXiv CS.AIRead the full story at ArXiv CS.AI
AI Analysis
Generated insight by OnAirToday AI
This research introduces a novel method for selecting representative subsets of prompts within LLM benchmarks, significantly reducing evaluation costs without compromising accuracy. By leveraging submodular functions on prompt embeddings, the approach offers a more efficient and scalable way to assess LLM performance across diverse tasks.
Powered by AI • Not a substitute for human analysisMore Insights →
Share
Filed under:AI Research
Comments
Keep comments relevant and respectful. No links, advertising, self-promotion, or spam.