# Policy-Grounded Dynamic Facet Suggestions for Job Search

arXiv: https://arxiv.org/abs/2605.16479 · HTML: https://mlsanity.com/paper/2605.16479/

## 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 (most cited first, 16 of 16)

- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [Towards General Text Embeddings with Multi-stage Contrastive Learning](https://mlsanity.com/paper/2308.03281/) (2023)
- [From Generation to Judgment: Opportunities and Challenges of LLM-as-a-judge](https://mlsanity.com/paper/2411.16594/) (2024)
- [Embedding-based Retrieval in Facebook Search](https://mlsanity.com/paper/2006.11632/) (2020)
- [BERT-QE: Contextualized Query Expansion for Document Re-ranking](https://mlsanity.com/paper/2009.07258/) (2020)
- [Are We on the Right Way to Assessing LLM-as-a-Judge?](https://mlsanity.com/paper/2512.16041/) (2025)
- [Generative Relevance Feedback with Large Language Models](https://mlsanity.com/paper/2304.13157/) (2023)
- [Using Word Embeddings for Automatic Query Expansion](https://mlsanity.com/paper/1606.07608/) (2016)
- [LLM-based Query Expansion Fails for Unfamiliar and Ambiguous Queries](https://mlsanity.com/paper/2505.12694/) (2025)
- [Deep Neural Networks for Query Expansion using Word Embeddings](https://mlsanity.com/paper/1811.03514/) (2018)
- [Powering Job Search at Scale: LLM-Enhanced Query Understanding in Job Matching Systems](https://mlsanity.com/paper/2509.09690/) (2025)

## 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.