EMNLP Findings2025
LaMP-Val: Large Language Models Empower Personalized Valuation in Auction
Jie Sun, Tianyu Zhang, Houcheng Jiang, Kexin Huang, Xiang Shu, Zhibo Zhu, Lintao Ma, Xingyu Lu, Jun Zhou, Junkang Wu, Chi Luo, An Zhang
摘要
Auctions are a vital economic mechanism used to determine the market value of goods or services through competitive bidding within a specific framework. However, much of the current research primarily focuses on the bidding algorithms used within auction mechanisms. This often neglects the potential benefits of incorporating individual users' unique preferences into the valuation process. Our theoretical and empirical analysis demonstrates that valuation errors can significantly impact the overall utility. To bridge this gap, we propose a personalized valuation framework, namely Large Language Models-powered Personalized Valuation (LaMP-Val), which integrates Large Language Models to incorporate personalized semantic preference into users valuation process. LaMP-Val integrating three components: data, learning, and evaluation. The data component tackles the challenge of building a novel dataset specifically for LLMs fine-tuning in personalized valuation modeling. The learning component introduces a diversity template to enhance LLMs' capacity for modeling finegrained personal valuation patterns. The evaluation component establishes a closed-loop system where LLM-generated valuations interact with bidding strategies and auction. It proposes two novel metrics to quantify valuation precision and bidding intention accuracy in personalized scenarios. Extensive experiments show that LaMP-Val more accurately captures personalized values and achieves greater profits than baseline approaches.
问 Lune
几分钟读透这篇 Paper,不用再花一下午。
Lune 能读完全文,也能读引用它的顶会 Paper,讲清它的结论、证据和局限,每一点都注明出自哪篇 Paper。不用硬啃,也不靠猜。
已有 1 篇顶会 Paper 引用了它。别等审稿人问起,先弄清它们发现了什么。
脉络
- LIFT: Language-Interfaced Fine-Tuning for Non-language Machine Learning Tasks 引用了 Language Models are Few-Shot Learners
- LIFT: Language-Interfaced Fine-Tuning for Non-language Machine Learning Tasks 引用了 Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
- A Survey on In-context Learning 引用了 Language Models are Few-Shot Learners
- A Survey on In-context Learning 引用了 Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
引用它的顶会 Paper1
它引用的 Paper12
- Language Models are Few-Shot LearnersTom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah 等NeurIPS 2020 · 64,255 次引用
- Chain-of-Thought Prompting Elicits Reasoning in Large Language ModelsJason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma 等NeurIPS 2022 · 22,562 次引用
- A Survey on In-context LearningQingxiu Dong, Lei Li, Damai Dai, Ce Zheng 等EMNLP 2024 · 479 次引用
- LIFT: Language-Interfaced Fine-Tuning for Non-language Machine Learning TasksTuan Dinh, Yuchen Zeng, Ruisu Zhang, Ziqian Lin 等NeurIPS 2022 · 222 次引用
- Robust Auction Design in the Auto-bidding WorldSantiago R. Balseiro, Yuan Deng, Jieming Mao, Vahab S. Mirrokni 等NeurIPS 2021 · 95 次引用
相关 Paper
- LLMs + Persona-Plug = Personalized LLMsJiongnan Liu, Yutao Zhu, Shuting Wang, Xiaochi Wei 等ACL 2025 · 19 次引用
- LaMP: When Large Language Models Meet PersonalizationAlireza Salemi, Sheshera Mysore, Michael Bendersky, Hamed ZamaniACL 2024
- Optimization Methods for Personalizing Large Language Models through Retrieval AugmentationAlireza Salemi, Surya Kallumadi, Hamed ZamaniSIGIR 2024 · 52 次引用
- LBM: Hierarchical Large Auto-Bidding Model via Reasoning and ActingYewen Li, Zhiyi Lyu, Peng Jiang, Qingpeng Cai 等WWW 2026
- Auctions with LLM SummariesAvinava Dubey, Zhe Feng, Rahul Kidambi, Aranyak Mehta 等KDD 2024 · 3 次引用
