The paper introduces a GPU‑optimized retrieval framework for LinkedIn’s semantic search, partitioning embeddings into eight category‑supervised segments and applying a min/median aggregation rule aligned with the existing relevance policy. A lightweight Stage‑1 scorer generates high‑recall candidates, while a two‑stage GPU architecture—FP8 coarse ranking followed by FP16 re‑ranking—boosts throughput and recall, achieving 99.6‑99.8% of full‑FP16 recall at over 500 QPS per shard. In A/B testing, the system raises exploratory‑query Precision@10 from 63.7% to 79.0% and navigational Precision@1 from 65.5% to 74.7%, with human evaluation confirming the improvement.
arXiv:2606.16661v2 Announce Type: replace-cross Abstract: Fixed-length chunking in Retrieval-Augmented Generation (RAG) often leads to boundary fragmentation, where critical evidence is split across...
arXiv:2608.24079v1 Announce Type: cross Abstract: A shared search-and-recommendation index must score new items from features alone because search has no exploration slot. In a public log covering bo...
Public institutions hold large volumes of sensitive documents and support tickets that cannot leave the premises, ruling out cloud-hosted language models entirely. We report on RAGAL, a retrieval-augmented assistant for the technical-support team of AFIR, the Romanian Agency for Financing Rural Investments, built and operated under three hard constraints: zero data egress (no external API calls, even for synthetic data), a read-only mandate (the assistant drafts, humans execute), and a single 8 GB consumer laptop as the only development and training machine.
arXiv:2606. 29947v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used as rerankers in recommender systems, with the expectation that semantic understanding will help in cold-start and long-tail regimes.
arXiv:2608. 14841v1 Announce Type: new Abstract: Long-document visual question answering (VQA) over documents of tens to hundreds of pages mixing text, tables, charts, and figures typically follows retrieve-then-read pipelines.
The paper investigates the trade‑off of using a shared search‑and‑recommendation index that scores new items purely from features, thereby keeping the index open to unseen items. Experiments on public logs show that a feature‑based tower can match warm‑item performance (Recall@20 0.9595 vs 0.9510) and a lexical baseline, while a full‑catalog check is inconclusive. The study also quantifies the cost of this openness on recommendation quality across several baselines, revealing that exact full‑softmax training improves recall but is impractical at catalog scale.
arXiv:2607. 29606v1 Announce Type: cross Abstract: A fundamental challenge of vector search is achieving consistently high recall while minimizing computational costs.
arXiv:2606. 04194v1 Announce Type: new Abstract: Retrieving the few past turns that answer a new query across long multi-session histories is the retrieval bottleneck behind long-term conversational memory (LoCoMo, LongMemEval).
arXiv:2607. 27692v1 Announce Type: cross Abstract: Top-$K$ sparse attention reduces the cost of Softmax and value aggregation by attending to only a small subset of key--value (KV) entries.
arXiv:2607. 16848v1 Announce Type: cross Abstract: Long-term memory is becoming a core component of LLM agents, but most memory benchmarks evaluate conversations or compact summaries, while research agents need to restore evidence from full scientific papers.
LLM-based query expansion improves retrieval by generating document-like passages. In hybrid retrieval, however, most evaluations fuse fixed top-$L$ dense and sparse rankings. Because the cutoff contr...
arXiv:2606. 26899v1 Announce Type: new Abstract: Embedding-based retrieval ranks items by their similarity to a query in a shared vector space and usually aims to return the highest-scoring items.