LLM-Powered Preference Elicitation in Combinatorial Assignment
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916614321995776 |
|---|---|
| author | Soumalias, Ermis Jiang, Yanchen Zhu, Kehang Curry, Michael Seuken, Sven Parkes, David C. |
| author_facet | Soumalias, Ermis Jiang, Yanchen Zhu, Kehang Curry, Michael Seuken, Sven Parkes, David C. |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_10308 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | LLM-Powered Preference Elicitation in Combinatorial Assignment Soumalias, Ermis Jiang, Yanchen Zhu, Kehang Curry, Michael Seuken, Sven Parkes, David C. Artificial Intelligence Computer Science and Game Theory Machine Learning 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. |
| title | LLM-Powered Preference Elicitation in Combinatorial Assignment |
| topic | Artificial Intelligence Computer Science and Game Theory Machine Learning |
| url | https://arxiv.org/abs/2502.10308 |