Paper

{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.04946v1</id>\n    <title>LocalSUG: Geography-Aware LLM for Query Suggestion in Local-Life Services</title>\n    <updated>2026-03-05T08:42:27Z</updated>\n    <link href='https://arxiv.org/abs/2603.04946v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.04946v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>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.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.CL'/>\n    <published>2026-03-05T08:42:27Z</published>\n    <arxiv:primary_category term='cs.CL'/>\n    <author>\n      <name>Jinwen Chen</name>\n      <arxiv:affiliation>Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing</arxiv:affiliation>\n      <arxiv:affiliation>School of Artificial Intelligence, Beihang University, China</arxiv:affiliation>\n    </author>\n    <author>\n      <name>Shuai Gong</name>\n      <arxiv:affiliation>Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing</arxiv:affiliation>\n      <arxiv:affiliation>School of Artificial Intelligence, Beihang University, China</arxiv:affiliation>\n    </author>\n    <author>\n      <name>Shiwen Zhang</name>\n      <arxiv:affiliation>Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing</arxiv:affiliation>\n      <arxiv:affiliation>School of Artificial Intelligence, Beihang University, China</arxiv:affiliation>\n    </author>\n    <author>\n      <name>Zheng Zhang</name>\n      <arxiv:affiliation>Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing</arxiv:affiliation>\n      <arxiv:affiliation>School of Artificial Intelligence, Beihang University, China</arxiv:affiliation>\n    </author>\n    <author>\n      <name>Yachao Zhao</name>\n      <arxiv:affiliation>Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing</arxiv:affiliation>\n      <arxiv:affiliation>School of Artificial Intelligence, Beihang University, China</arxiv:affiliation>\n    </author>\n    <author>\n      <name>Lingxiang Wang</name>\n      <arxiv:affiliation>Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing</arxiv:affiliation>\n      <arxiv:affiliation>School of Artificial Intelligence, Beihang University, China</arxiv:affiliation>\n    </author>\n    <author>\n      <name>Haibo Zhou</name>\n      <arxiv:affiliation>Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing</arxiv:affiliation>\n      <arxiv:affiliation>School of Artificial Intelligence, Beihang University, China</arxiv:affiliation>\n    </author>\n    <author>\n      <name>Yuan Zhan</name>\n      <arxiv:affiliation>Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing</arxiv:affiliation>\n      <arxiv:affiliation>School of Artificial Intelligence, Beihang University, China</arxiv:affiliation>\n    </author>\n    <author>\n      <name>Wei Lin</name>\n      <arxiv:affiliation>Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing</arxiv:affiliation>\n      <arxiv:affiliation>School of Artificial Intelligence, Beihang University, China</arxiv:affiliation>\n    </author>\n    <author>\n      <name>Hainan Zhang</name>\n      <arxiv:affiliation>Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing</arxiv:affiliation>\n      <arxiv:affiliation>School of Artificial Intelligence, Beihang University, China</arxiv:affiliation>\n    </author>\n  </entry>"
}