mlsanityData to 7 Oct 2026

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

arXiv 2603.04946 ↗First posted 5 Mar 2026cs.CLcited by 0

On the map: LLM alignment / RLHF / preference optimisation → Preference alignment for recommenders and RAG

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.

Key facts. No citing papers in the map yet (data through 7 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.

Builds on

24 of 38 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024On Softmax Direct Preference Optimization for Recommendation13 Jun

Other references · 23

  1. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 7,916
  2. 2016Wide & Deep Learning for Recommender Systemscited by 745
  3. 2022Autoregressive Image Generation using Residual Quantizationcited by 706
  4. 2017DeepFM: A Factorization-Machine based Neural Network for CTR Predictioncited by 673
  5. 2023C-Pack: Packed Resources For General Chinese Embeddingscited by 556
  6. 2017Deep Interest Network for Click-Through Rate Predictioncited by 541
  7. 2018Deep Interest Evolution Network for Click-Through Rate Predictioncited by 336
  8. 2019Deep Learning Recommendation Model for Personalization and Recommendation Systemscited by 327
  9. 2025OneRec: Unifying Retrieve and Rank with Generative Recommender and Iterative Preference Alignmentcited by 167
  10. 2025MTGR: Industrial-Scale Generative Recommendation Framework in Meituancited by 47
  11. 2025Sparse Meets Dense: Unified Generative Recommendations with Cascaded Sparse-Dense Representationscited by 35
  12. 2025PLUM: Adapting Pre-trained Language Models for Industrial-scale Generative Recommendationscited by 27
11 more
  1. 2025REG4Rec: Reasoning-Enhanced Generative Model for Large-Scale Recommendation Systemscited by 18
  2. 2024Non-autoregressive Generative Models for Reranking Recommendationcited by 17
  3. 2025OneSug: The Unified End-to-End Generative Framework for E-commerce Query Suggestioncited by 13
  4. 2025PinFM: Foundation Model for User Activity Sequences at a Billion-scale Visual Discovery Platformcited by 8
  5. 2025LocalSearchBench: Benchmarking Agentic Search in Real-World Local Life Servicescited by 7
  6. 2025FIM: Frequency-Aware Multi-View Interest Modeling for Local-Life Service Recommendationcited by 6
  7. 2025EGA-V2: An End-to-end Generative Framework for Industrial Advertisingcited by 5
  8. 2025Act-With-Think: Chunk Auto-Regressive Modeling for Generative Recommendationcited by 4
  9. 2022AutoFAS: Automatic Feature and Architecture Selection for Pre-Ranking Systemcited by 3
  10. 2024MOBIUS: Towards the Next Generation of Query-Ad Matching in Baidu's Sponsored Searchcited by 3
  11. 2025Generative Click-through Rate Prediction with Applications to Search Advertisingcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025LocalGPT: Benchmarking and Advancing Large Language Models for Local Life Services in Meituan
  2. 2026Enhancing Local Life Service Recommendation with Agentic Reasoning in Large Language Model
  3. 2026SCOUT: Supply-Aware Cold-Start Proactive Query Suggestion for Travel Search ↗
  4. 2025LLM-Aligned Geographic Item Tokenization for Local-Life Recommendation
  5. 2024A Survey of Query Optimization in Large Language Models
  6. 2025AskNearby: An LLM-Based Application for Neighborhood Information Retrieval and Personalized Cognitive-Map Recommendations
  7. 2025GR-LLMs: Recent Advances in Generative Recommendation Based on Large Language Models
  8. 2025Rethinking LLM-Based Recommendations: A Personalized Query-Driven Parallel Integration