用大模型替代人工提问，一键获取偏好，提升组合分配效率
LLM-Powered Preference Elicitation in Combinatorial Assignment
- 用大模型作为人类偏好代理，一次响应完成传统多轮提问
- 在课程分配任务中提升分配效率最高达20%
- 对不同模型和报告质量差异具有强鲁棒性，适合大规模应用
我们研究大语言模型（LLMs）作为人类代理在组合分配中简化偏好获取（PE）的潜力。传统方法依赖多轮交互式提问，而LLMs提供单次响应的替代方案，显著降低人力成本。本文提出一种与当前最优机器学习驱动偏好获取方法兼容的框架，解决了LLMs带来的响应波动性和计算开销等新挑战。我们在经典的课程分配领域实验评估了该方法的效率，并探究成功所需模型能力。结果表明，该方法可将分配效率提升最高达20%，且在不同LLMs及报告质量差异下表现稳健。
原文摘要 · Abstract (English)
We study the potential of large language models (LLMs) as proxies for humans to simplify preference elicitation (PE) in combinatorial assignment. While traditional PE methods rely on iterative queries to capture preferences, LLMs offer a one-shot alternative with reduced human effort. We propose a framework for LLM proxies that can work in tandem with SOTA ML-powered preference elicitation schemes. Our framework handles the novel challenges introduced by LLMs, such as response variability and increased computational costs. We experimentally evaluate the efficiency of LLM proxies against human queries in the well-studied course allocation domain, and we investigate the model capabilities required for success. We find that our approach improves allocative efficiency by up to 20%, and these results are robust across different LLMs and to differences in quality and accuracy of reporting.
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。