facility-location

Tag

Cards List
#facility-location

Coresets Before Score Sets: Evaluation-Unsupervised Prompt Subset Selection for LLM Benchmarks

arXiv cs.AI ↗ · 2026-07-14 Cached

This paper proposes a submodular coreset selection method for LLM benchmarks that selects a subset of prompts without using model evaluation outcomes, achieving score preservation across 35 benchmarks and 18 LLMs.

0 favorites 0 likes
← Back to home

Submit Feedback