mlsanityData to 14 Oct 2026

A Unified Structured Query Understanding Framework for Industrial Semantic Search

arXiv 2605.27441 ↗First posted 22 May 2026cs.IR cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Query understanding in large-scale industrial search systems is typically implemented as a cascade of disparate, task-specific components. While individually optimizable, this fragmented architecture incurs high maintenance overhead and results in inconsistent behaviors, particularly for long-tail queries. In this work, we propose and deploy a unified structured query understanding system that consolidates these heterogeneous functions into a single Small Language Model (SLM) that performs schema-constrained generation. To address the data bottlenecks inherent in unified modeling, we introduce Query Illuminator, a dual-purpose framework serving as: (i) a teacher model for high-quality auto-annotation and distillation, and (ii) a surrogate judge for scalable evaluation where human labels are scarce. We validate this approach through extensive offline and online tests within LinkedIn's Job Search system. Furthermore, we demonstrate the framework's horizontal extensibility through a cross-domain case study on People Search. The results show improved user engagement and reduced operational costs, achieved while satisfying strict low-latency serving constraints on limited GPU resources.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 23 of its 48 references that are in the map. First posted on arXiv 22 May 2026.

Builds on

23 of 48 references.

References · 23

  1. 2022Training language models to follow instructions with human feedbackcited by 15,971
  2. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
  3. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  4. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,944
  5. 2018GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understandingcited by 4,899
  6. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,182
  7. 2023G-Eval: NLG Evaluation using GPT-4 with Better Human Alignmentcited by 2,276
  8. 2021Multitask Prompted Training Enables Zero-Shot Task Generalizationcited by 1,470
  9. 2020It's Not Just Size That Matters: Small Language Models Are Also Few-Shot Learnerscited by 669
  10. 2023UltraFeedback: Boosting Language Models with Scaled AI Feedbackcited by 406
  11. 2023Large Language Model based Long-tail Query Rewriting in Taobao Searchcited by 62
  12. 2024GenQREnsemble: Zero-Shot LLM Ensemble Prompting for Generative Query Reformulationcited by 23
11 more
  1. 2022QUILL: Query Intent with Large Language Models using Retrieval Augmentation and Multi-stage Distillationcited by 21
  2. 2024Query Routing for Homogeneous Tools: An Instantiation in the RAG Scenariocited by 10
  3. 2025Put Teacher in Student's Shoes: Cross-Distillation for Ultra-compact Model Compression Frameworkcited by 8
  4. 2024Exploring Query Understanding for Amazon Product Searchcited by 6
  5. 2025Personalized Query Auto-Completion for Long and Short-Term Interests with Adaptive Detoxification Generationcited by 4
  6. 2023DeepTagger: Knowledge Enhanced Named Entity Recognition for Web-Based Ads Queriescited by 3
  7. 2020Natural language technology and query expansion: issues, state-of-the-art and perspectivescited by 2
  8. 2024Study of Workload Interference with Intelligent Routing on Dragonflycited by 2
  9. 2025Powering Job Search at Scale: LLM-Enhanced Query Understanding in Job Matching Systemscited by 2
  10. 2025GREAT: Guiding Query Generation with a Trie for Recommending Related Search about Video at Kuaishoucited by 1
  11. 2025MixLM: High-Throughput and Effective LLM Ranking via Text-Embedding Mix-Interactioncited by 1

Built on by

Not cited yet.