Efficient Cost-Aware LLM Evaluation via Bayesian Bandit Gittins Indices

2026-09-21

AI Summary

本文提出GittinsEval方法，通过成本敏感的贝叶斯多臂赌博机策略有效降低大规模语言模型配置评估的成本和时间。

Abstract

Exhaustively evaluating every candidate LLM configuration on every benchmark item to identify a high-performing one is costly. We formulate configuration selection as a cost-aware Bayesian bandit problem and propose GittinsEval, which draws on the Bayesian-optimal Gittins policy to determine which configuration to evaluate next and when to stop. We extend the policy with an anytime recommendation rule over both fully and partially evaluated configurations, using an LCB-style score to account for posterior uncertainty. GittinsEval is computationally efficient, requiring only lightweight online updates after offline precomputation. Across GSM8K, PIQA, AlpacaEval, and MMLU response matrices, GittinsEval is consistently competitive, with particularly strong gains over configuration-level Bayesian optimization on large-example benchmarks and over cost-unaware bandit baselines on large-candidate tasks. Crucially, GittinsEval often attains near-zero simple regret using only 1% to 2% of the exhaustive-evaluation cost; it also offers an adaptive stopping rule that typically triggers at 1% to 10%.

Problem

• Cost-Aware
• LLM Evaluation
• Bayesian Bandit
• Gittins Indices
• Configuration Selection

Innovation

• Cost-aware Bayesian bandit
• Gittins policy
• LCB-style score
• Adaptive stopping rule
• Efficient online updates