LLM-Powered Preference Elicitation in Combinatorial Assignment
This work addresses the problem of efficient preference elicitation for combinatorial assignment, which is significant for applications where human preferences need to be accurately captured, such as course allocation.
The authors tackled the problem of preference elicitation in combinatorial assignment and achieved an improvement in allocative efficiency of up to 20% using large language models as proxies for humans. This result was found to be robust across different models and reporting qualities.
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.