Multilingual Semantic Retrieval for Apple Music Search

Efficient GPU Retrieval for Semantic Search

A policy-aligned retrieval framework that improves offline relevance over a matched-capacity baseline, with gains broadly distributed across facet combinations, and serves this framework with a two-stage GPU architecture.

From Queries to Playlists: An LLM-Driven Architecture for Semantic Music Search at Scale

A core task for music streaming platforms is retrieving and ranking tracks in response to user queries over multi-million-track catalogs. Existing approaches either rely on tag-based, entity-centric retrieval and recommendation, which struggle with implicit and subjective queries that fall outside a predefined tag vocabulary, or on recent LLM-based generative methods that circumvent this limitation but are prone to hallucinations and factual errors. We introduce a semantic playlist generation service that retrieves and ranks tracks based on meaning rather than keyword overlap, while avoiding hallucination-related failures. Each track is represented as structured text combining metadata, lyrics, and descriptive attributes, and both user queries and track representations are encoded into a shared embedding space using an LLM. A cross-encoder reranker built on the same backbone refines candidate ranking, and its signals are distilled into the embedder to reduce serving cost. In offline and production evaluations, our semantic vector-search pipeline achieves the highest playlist quality, improving Precision@10 from 64% with faceted search and 74% with direct LLM generation to 81%, while remaining compatible with low-latency, large-scale deployment. In an online A/B test on smart-speaker traffic, routing a share of playlist requests to our system yields a consistent double-digit relative uplift in Average Time Spent, indicating that meaning-aware retrieval substantially enhances user engagement and supports broader production rollout.

ADAPTIVE MULTI-STAGE VECTOR RETRIEVAL FOR RETRIEVAL-AUGMENTED GENERATION

The Adaptive Multi-Stage Vector Retrieval (AMSVR) framework is proposed, prioritising weighted, drift-resistant composition over uniform fusion, and offers tailored configurations: AMSVR-Scientific (dense + tuned hybrid) peaks at NDCG@10 = 0.7570 on SciFact, while AMSVR-Full (seven stages) targets broader, noisier corpora where Recall@100 matters most.

CeQe: Grounding Lexical Retrieval in Semantic Evidence

This work presents Cross-Encoder Query Expansion (CE-QE), which reads the per-token relevance attributions of a cross-encoder applied to top semantic search results, selects the terms the cross-encoder treats as decisive, and appends them to the BM25 query.

Sequran: Composite Scoring and Reranking Techniques for Refining Quran Search Engine Results

Query Expansion Is More Than Generation: Improving Dense Retrieval through Better Integration

This work introduces AnchorQE, a training-free method that separately encodes the original query and its expansion before interpolating them, and shows that AnchorQE improves retrieval effectiveness by up to 12.89% when compared to widely-used expansion-only or text-level concatenation baselines across TREC-DL, LoTTE, and BEIR.