mlsanityData to 14 Oct 2026

Policy-Grounded Dynamic Facet Suggestions for Job Search

arXiv 2605.16479 ↗First posted 15 May 2026cs.IR cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Job seekers often initiate search with short, underspecified queries. At LinkedIn, over 80% of job-related queries contain three or fewer keywords, making accurate user intent inference and relevant job retrieval particularly challenging. We present dynamic facet suggestion (DFS), an interactive query refinement mechanism that facilitates intent disambiguation by surfacing personalized semantic attributes conditioned on the joint user-query context in real time. We propose a policy-grounded, retrieval-augmented ranking framework for facet suggestion, comprising offline taxonomy curation, embedding-based retrieval of top-K candidates, and distilled small language model (SLM) based candidate scoring. The system is optimized for real-time serving via pointwise single-token scoring with batching and prefix caching. Offline evaluation demonstrates high precision for generated suggestions, and online A/B tests show significant improvements in suggestion engagement and job search outcomes.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 16 of its 35 references that are in the map. First posted on arXiv 15 May 2026.

Builds on

16 of 35 references.

References · 16

  1. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  3. 2025Qwen3 Technical Reportcited by 8,820
  4. 2018Representation Learning with Contrastive Predictive Codingcited by 7,777
  5. 2023Qwen Technical Reportcited by 3,344
  6. 2022Constitutional AI: Harmlessness from AI Feedbackcited by 3,050
  7. 2023Towards General Text Embeddings with Multi-stage Contrastive Learningcited by 723
  8. 2024From Generation to Judgment: Opportunities and Challenges of LLM-as-a-judgecited by 494
  9. 2020Embedding-based Retrieval in Facebook Searchcited by 156
  10. 2020BERT-QE: Contextualized Query Expansion for Document Re-rankingcited by 40
  11. 2025Are We on the Right Way to Assessing LLM-as-a-Judge?cited by 24
  12. 2023Generative Relevance Feedback with Large Language Modelscited by 20
4 more
  1. 2016Using Word Embeddings for Automatic Query Expansioncited by 14
  2. 2025LLM-based Query Expansion Fails for Unfamiliar and Ambiguous Queriescited by 10
  3. 2018Deep Neural Networks for Query Expansion using Word Embeddingscited by 7
  4. 2025Powering Job Search at Scale: LLM-Enhanced Query Understanding in Job Matching Systemscited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026De-conflating Preference and Qualification: Constrained Dual-Perspective Reasoning for Job Recommendation with Large Language Models
  2. 2026Semantic Search At LinkedIn
  3. 2026An Efficient Long-Context Ranking Architecture With Calibrated LLM Distillation: Application to Person-Job Fit
  4. 2024LiRank: Industrial Large Scale Ranking Models at LinkedIn
  5. 2026Unified Semantic Modeling Framework for Large-Scale Job Understanding at LinkedIn
  6. 2026Synapse: Evolving Job-Person Fit with Explainable Two-phase Retrieval and LLM-guided Genetic Resume Optimization
  7. 2026GenFacet: End-to-End Generative Faceted Search via Multi-Task Preference Alignment in E-Commerce ↗
  8. 2026High Fidelity Textual User Representation over Heterogeneous Sources via Reinforcement Learning