Modernizing Facebook Scoped Search: Keyword And Embedding Hybrid Retrieval With LLM Evaluation

Abstract

Beyond general web-scale search, social network search uniquely enables users to retrieve information and discover potential connections within their social context. We introduce a framework of modernized Facebook Group Scoped Search by blending traditional keyword-based retrieval with embedding-based retrieval (EBR) to improve the search relevance and diversity of search results. Our system integrates semantic retrieval into the existing keyword search pipeline, enabling users to discover more contextually relevant group posts. To rigorously assess the impact of this blended approach, we introduce a novel evaluation framework that leverages large language models (LLMs) to perform offline relevance assessments, providing scalable and consistent quality benchmarks. Our results demonstrate that the blended retrieval system significantly enhances user engagement and search quality, as validated by both online metrics and LLM-based evaluation. This work offers practical insights for deploy

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keysu2025modernizing

Related papers

• Embedding-based Retrieval In Facebook Search (2020)18.09
• Que2engage: Embedding-based Retrieval For Relevant And Engaging Products At Facebook Marketplace (2023)6.34
• Search-adaptor: Embedding Customization For Information Retrieval (2023)0.00
• Vectorsearch: Enhancing Document Retrieval With Semantic Embeddings And Optimized Search (2024)0.00
• Integrity And Junkiness Failure Handling For Embedding-based Retrieval: A Case Study In Social Network Search (2023)3.58
• Smart Multi-modal Search: Contextual Sparse And Dense Embedding Integration In Adobe Express (2024)0.00
• Event-enhanced Retrieval In Real-time Search (2024)0.95
• Rethinking Hybrid Retrieval: When Small Embeddings And LLM Re-ranking Beat Bigger Models (2025)0.00