# LocalSUG: City-Preference-Enhanced LLM for Query Suggestion in Local-Life Services

arXiv: https://arxiv.org/abs/2603.04946 · HTML: https://mlsanity.com/paper/2603.04946/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Preference alignment for recommenders and RAG, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 24 of its 38 references that are in the map.
- First posted on arXiv 5 Mar 2026.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Preference alignment for recommenders and RAG](https://mlsanity.com/alignment/preference-alignment-for-recommenders-and-rag/)

## Builds on (most cited first, 24 of 24)

- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Wide & Deep Learning for Recommender Systems](https://mlsanity.com/paper/1606.07792/) (2016)
- [Autoregressive Image Generation using Residual Quantization](https://mlsanity.com/paper/2203.01941/) (2022)
- [DeepFM: A Factorization-Machine based Neural Network for CTR Prediction](https://mlsanity.com/paper/1703.04247/) (2017)
- [C-Pack: Packed Resources For General Chinese Embeddings](https://mlsanity.com/paper/2309.07597/) (2023)
- [Deep Interest Network for Click-Through Rate Prediction](https://mlsanity.com/paper/1706.06978/) (2017)
- [Deep Interest Evolution Network for Click-Through Rate Prediction](https://mlsanity.com/paper/1809.03672/) (2018)
- [Deep Learning Recommendation Model for Personalization and Recommendation Systems](https://mlsanity.com/paper/1906.00091/) (2019)
- [OneRec: Unifying Retrieve and Rank with Generative Recommender and Iterative Preference Alignment](https://mlsanity.com/paper/2502.18965/) (2025)
- [On Softmax Direct Preference Optimization for Recommendation](https://mlsanity.com/paper/2406.09215/) (2024)
- [MTGR: Industrial-Scale Generative Recommendation Framework in Meituan](https://mlsanity.com/paper/2505.18654/) (2025)
- [Sparse Meets Dense: Unified Generative Recommendations with Cascaded Sparse-Dense Representations](https://mlsanity.com/paper/2503.02453/) (2025)
- [PLUM: Adapting Pre-trained Language Models for Industrial-scale Generative Recommendations](https://mlsanity.com/paper/2510.07784/) (2025)
- [Non-autoregressive Generative Models for Reranking Recommendation](https://mlsanity.com/paper/2402.06871/) (2024)
- [REG4Rec: Reasoning-Enhanced Generative Model for Large-Scale Recommendation Systems](https://mlsanity.com/paper/2508.15308/) (2025)
- [OneSug: The Unified End-to-End Generative Framework for E-commerce Query Suggestion](https://mlsanity.com/paper/2506.06913/) (2025)
- [PinFM: Foundation Model for User Activity Sequences at a Billion-scale Visual Discovery Platform](https://mlsanity.com/paper/2507.12704/) (2025)
- [LocalSearchBench: Benchmarking Agentic Search in Real-World Local Life Services](https://mlsanity.com/paper/2512.07436/) (2025)
- [FIM: Frequency-Aware Multi-View Interest Modeling for Local-Life Service Recommendation](https://mlsanity.com/paper/2504.17814/) (2025)
- [EGA-V2: An End-to-end Generative Framework for Industrial Advertising](https://mlsanity.com/paper/2505.17549/) (2025)
- [Act-With-Think: Chunk Auto-Regressive Modeling for Generative Recommendation](https://mlsanity.com/paper/2506.23643/) (2025)
- [AutoFAS: Automatic Feature and Architecture Selection for Pre-Ranking System](https://mlsanity.com/paper/2205.09394/) (2022)
- [MOBIUS: Towards the Next Generation of Query-Ad Matching in Baidu's Sponsored Search](https://mlsanity.com/paper/2409.03449/) (2024)
- [Generative Click-through Rate Prediction with Applications to Search Advertising](https://mlsanity.com/paper/2507.11246/) (2025)

## Built on by (most cited first, 1 of 1)

- [WeGR: Unified Generative Retrieval for Industrial Search Systems in WeChat](https://mlsanity.com/paper/2610.16979/) (2026)

## Abstract (arXiv)

In local-life service platforms, query suggestion reduces user effort by generating candidate queries from input prefixes. Traditional multi-stage systems rely heavily on historical popular queries, limiting their ability to capture long-tail and emerging demand. Although LLMs provide strong semantic generalization, their deployment in local-life services faces three challenges: insufficient city-preference awareness, exposure bias in preference optimization, and strict online latency constraints. We propose LocalSUG, an LLM-based query suggestion framework for local-life services. LocalSUG mines city-preference-enhanced candidates from term co-occurrence and injects them into prompts as dynamic references rather than fusing them into model parameters. This allows the model to adapt to changing city preferences, such as merchant openings or closures, while reducing stale or locally invalid suggestions. We further introduce a beam-search-driven GRPO algorithm to align training with inference-time decoding and optimize relevance together with business-oriented rewards. Finally, quality-aware beam acceleration and vocabulary pruning reduce online latency while preserving generation quality. Offline evaluations and large-scale online A/B testing show that LocalSUG improves CTR by +0.35% and reduces the no-result rate by 3.98%, demonstrating its effectiveness in real-world deployment.