TensorX
返回文献探索

Paper · arXiv 2410.13804

BenTo: Benchmark Task Reduction with In-Context Transferability

Hongyu Zhao, Ming Li, Lichao Sun, Tianyi Zhou

20 upvotesOctober 17, 2024arXiv 预印本
AI 摘要

Efficiently reducing the number of tasks for evaluating large language models with minimal impact on evaluation quality using a transferability metric based on in-context learning.

large language modelsevaluationfacility location functiontransferabilityin-context learning

Abstract

Evaluating large language models (LLMs) is costly: it requires the generation and examination of LLM outputs on a large-scale benchmark of various tasks. This paper investigates how to efficiently reduce the tasks used to benchmark LLMs without affecting the evaluation quality. Our study reveals that task transferability and relevance provide critical information to identify the most representative subset of tasks via optimizing a facility location function. We propose a practically efficient metric for estimating the transferability between two tasks via in-context learning (ICL). By analyzing the pairwise transferability, we can reduce tasks in a modern LLM benchmark (e.g., MMLU or FLAN) to 5% while inducing only a <4% difference to the evaluation on the original benchmark. Compared to prior works, our method is training-free, gradient-free, and highly efficient requiring ICL only.

北京市昌平区探索星信息技术及软件开发工作室

京ICP备2026059466号
BenTo: Benchmark Task Reduction with In-Context Transferability | TensorX