# Accelerated Preference Elicitation with LLM-Based Proxies

arXiv: https://arxiv.org/abs/2501.14625 · HTML: https://mlsanity.com/paper/2501.14625/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 61 references that are in the map.
- First posted on arXiv 24 Jan 2025.

## Builds on (most cited first, 9 of 9)

- [Investigating ChatGPT's Potential to Assist in Requirements Elicitation Processes](https://mlsanity.com/paper/2307.07381/) (2023)
- [Bayesian Optimization with LLM-Based Acquisition Functions for Natural Language Preference Elicitation](https://mlsanity.com/paper/2405.00981/) (2024)
- [Deep Learning-powered Iterative Combinatorial Auctions](https://mlsanity.com/paper/1907.05771/) (2019)
- [Machine Learning-powered Iterative Combinatorial Auctions](https://mlsanity.com/paper/1911.08042/) (2019)
- [Bayesian Optimization-based Combinatorial Assignment](https://mlsanity.com/paper/2208.14698/) (2022)
- [Monotone-Value Neural Networks: Exploiting Preference Monotonicity in Combinatorial Assignment](https://mlsanity.com/paper/2109.15117/) (2021)
- [Fast Iterative Combinatorial Auctions via Bayesian Learning](https://mlsanity.com/paper/1809.05340/) (2018)
- [Machine Learning-Powered Combinatorial Clock Auction](https://mlsanity.com/paper/2308.10226/) (2023)
- [Efficient Preference Elicitation in Iterative Combinatorial Auctions with Many Participants](https://mlsanity.com/paper/2403.19075/) (2024)

## Built on by (most cited first, 9 of 9)

- [Game Theory Meets Large Language Models: A Systematic Survey with Taxonomy and New Frontiers](https://mlsanity.com/paper/2502.09053/) (2025)
- [LLM Bidders Preserve the Mechanism-Level Orderings of Human Bidders](https://mlsanity.com/paper/2507.09083/) (2025)
- [LLM-Powered Preference Elicitation in Combinatorial Assignment](https://mlsanity.com/paper/2502.10308/) (2025)
- [Cold-Start Personalization via Training-Free Priors from Structured World Models](https://mlsanity.com/paper/2602.15012/) (2026)
- [Matching Markets Meet LLMs: Algorithmic Reasoning with Ranked Preferences](https://mlsanity.com/paper/2506.04478/) (2025)
- [Incentive-Aligned Multi-Source LLM Summaries](https://mlsanity.com/paper/2509.25184/) (2025)
- [SEED-SET: Scalable Evolving Experimental Design for System-level Ethical Testing](https://mlsanity.com/paper/2603.01630/) (2026)
- [One Model, Two Markets: Bid-Aware Generative Recommendation](https://mlsanity.com/paper/2603.22231/) (2026)
- [Preference Reasoning under Indeterminacy in Large Language Models](https://mlsanity.com/paper/2608.18631/) (2026)

## Abstract (arXiv)

Bidders in combinatorial auctions face significant challenges when describing their preferences to an auctioneer. Classical work on preference elicitation focuses on query-based techniques inspired from proper learning--often via proxies that interface between bidders and an auction mechanism--to incrementally learn bidder preferences as needed to compute efficient allocations. Although such elicitation mechanisms enjoy theoretical query efficiency, the amount of communication required may still be too cognitively taxing in practice. We propose a family of efficient LLM-based proxy designs for eliciting preferences from bidders using natural language. Our proposed mechanism combines LLM pipelines and DNF-proper-learning techniques to quickly approximate preferences when communication is limited. To validate our approach, we create a testing sandbox for elicitation mechanisms that communicate in natural language. In our experiments, our most promising LLM proxy design reaches approximately efficient outcomes with five times fewer queries than classical proper learning based elicitation mechanisms.