用强化学习选关键测试题，大幅降低大模型评估成本
Active Evaluation Acquisition for Efficient LLM Benchmarking
- 基于强化学习选择代表性测试样本，利用样本间依赖关系预测结果
- 仅需评估少量样本，即可准确估计模型整体性能（相比之前方法减少60%以上）
- 适合需要高效评测大模型能力的研究者和工程团队
随着大语言模型日益复杂，大量大规模基准测试被开发以全面评估其能力。这些基准通常包含数百甚至上千个不同数据集和提示，但全面评估带来巨大的计算、资金与时间开销。本文提出一种基于学习策略的主动评估采样方法，通过建模测试样本间的依赖关系，仅需对选定子集进行真实评估，即可准确预测其余样本的表现。我们系统探索多种子集选择策略，并引入一种新的基于强化学习的策略以捕捉依赖结构。实验表明，该方法显著减少所需评估提示数量，同时保持与现有方法相当的性能估计准确性。
原文摘要 · Abstract (English)
As large language models (LLMs) become increasingly versatile, numerous large scale benchmarks have been developed to thoroughly assess their capabilities. These benchmarks typically consist of diverse datasets and prompts to evaluate different aspects of LLM performance. However, comprehensive evaluations on hundreds or thousands of prompts incur tremendous costs in terms of computation, money, and time. In this work, we investigate strategies to improve evaluation efficiency by selecting a subset of examples from each benchmark using a learned policy. Our approach models the dependencies across test examples, allowing accurate prediction of the evaluation outcomes for the remaining examples based on the outcomes of the selected ones. Consequently, we only need to acquire the actual evaluation outcomes for the selected subset. We rigorously explore various subset selection policies and introduce a novel RL-based policy that leverages the captured dependencies. Empirical results demonstrate that our approach significantly reduces the number of evaluation prompts required while maintaining accurate performance estimates compared to previous methods.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。