LocalSUG: Geography-Aware LLM for Query Suggestion in Local-Life Services
Jinwen Chen (1, 2), Shuai Gong, Shiwen Zhang (1, 2), Zheng Zhang, Yachao Zhao, Lingxiang Wang (1, 2), Haibo Zhou, Yuan Zhan, Wei Lin, Hainan Zhang (1, 2) ((1) Beijing Advanced Innovation Center for Future Blockchain, Privacy Computing, (2) School of Artificial Intelligence

TL;DR
LocalSUG is a geography-aware LLM framework designed for query suggestion in local-life services, addressing geographic grounding, bias, and latency challenges to improve user experience and business metrics.
Contribution
We propose a novel LLM-based query suggestion framework with geographic grounding, bias reduction, and latency optimization for local-life service platforms.
Findings
CTR increased by +0.35% in online tests
Low/no-result rate reduced by 2.56%
Effective in real-world deployment
Abstract
In local-life service platforms, the query suggestion module plays a crucial role in enhancing user experience by generating candidate queries based on user input prefixes, thus reducing user effort and accelerating search. Traditional multi-stage cascading systems rely heavily on historical top queries, limiting their ability to address long-tail demand. While LLMs offer strong semantic generalization, deploying them in local-life services introduces three key challenges: lack of geographic grounding, exposure bias in preference optimization, and online inference latency. To address these issues, we propose LocalSUG, an LLM-based query suggestion framework tailored for local-life service platforms. First, we introduce a city-aware candidate mining strategy based on term co-occurrence to inject geographic grounding into generation. Second, we propose a beam-search-driven GRPO algorithm…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsInformation Retrieval and Search Behavior · Caching and Content Delivery · Web Data Mining and Analysis
