LocalSUG: Geography-Aware LLM for Query Suggestion in Local-Life Services

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 that aligns training with inference-time decoding, reducing exposure bias in autoregressive generation. A multi-objective reward mechanism further optimizes both relevance and business-oriented metrics. Finally, we develop quality-aware beam acceleration and vocabulary pruning techniques that significantly reduce online latency while preserving generation quality. Extensive offline evaluations and large-scale online A/B testing demonstrate that LocalSUG improves click-through rate (CTR) by +0.35% and reduces the low/no-result rate by 2.56%, validating its effectiveness in real-world deployment.