Topic - Edition
Suppose you run paginated search in your application, or a RAG pipeline where the top ten retrieved documents feed a model. One of your users searches for a recipe collection for "chocolate cake." Page one ends with…
arXiv:2609.30177v1 Announce Type: new Abstract: Query understanding (QU) plays a critical role in production search systems, translating raw user queries into search execution plans that drive downstream retrieval and…
arXiv:2609.30205v1 Announce Type: new Abstract: Large language model (LLM)-based clinical assistants are increasingly being integrated into electronic health record (EHR) systems, transforming how clinicians retrieve…
arXiv:2609.30009v1 Announce Type: new Abstract: Financial institutions operate under dense, frequently amended rulebooks, and answering a compliance question correctly requires not only fluency but verifiable grounding…
arXiv:2609.29455v1 Announce Type: new Abstract: Document retrieval is a crucial component of many modern AI systems, directly influencing their effectiveness, robustness, and fairness in downstream tasks. While recent…
arXiv:2609.29182v1 Announce Type: new Abstract: Numerical embeddings for click-through rate (CTR) prediction are built on a convenient but restrictive premise: a scalar has one representation. This premise conflates…
arXiv:2609.28765v1 Announce Type: cross Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) performs well on problems with clear rewards, such as mathematics and coding, but whether it also works where the…
arXiv:2609.29453v1 Announce Type: cross Abstract: We formalize slate recommendation as a randomized score learner followed by deterministic selection. First, an appropriately scoped differential-privacy guarantee passes…
arXiv:2609.29661v1 Announce Type: cross Abstract: Most agentic question answering (QA) systems do an important part of their semantic work at the worst possible time: every time someone asks a question. When a corpus…
arXiv:2602.23012v2 Announce Type: replace Abstract: Predicting continuous values such as watch-time and gross merchandise value (GMV) is a core problem in industrial recommendation systems. Its inherent difficulty stems…
arXiv:2609.29815v1 Announce Type: new Abstract: Sequential recommendation aims to predict users' future interests from their historical interactions. Although Large Language Models (LLMs) capture rich item semantics,…
arXiv:2609.29191v1 Announce Type: cross Abstract: Sensitive information is defined by domain and intent, not a universal category, yet redaction systems such as privacy filters and named-entity recognizers fix a…
arXiv:2609.30087v1 Announce Type: cross Abstract: We consider the decision of whether to return an existing draft answer or revise it using retrieved evidence, as in answer-revision systems. Draft confidence estimates…
arXiv:2609.29703v1 Announce Type: cross Abstract: AI-agent evaluations usually inspect a final answer, yet error may enter through evidence, retrieval, prompting, generation or decision mapping. We introduce a…
arXiv:2609.28653v1 Announce Type: new Abstract: Retrieval-augmented question answering requires control decisions about when to decompose a question, search, reformulate, extract evidence, synthesize facts, verify…
arXiv:2609.29618v1 Announce Type: cross Abstract: We report an exploratory, single-seed ablation of TALH (Adaptive Latent Hybrid), a decoder-only language model with parallel Multi-head Latent Attention (MLA) and a…
arXiv:2609.29609v1 Announce Type: new Abstract: Modeling the underlying user intent is crucial for recommendation, but existing methods struggle with the inherent uncertainty and the dynamic, hierarchical nature of user…
arXiv:2609.28972v1 Announce Type: new Abstract: Cross-country recommendation on modern e-commerce platforms is typically deployed with disjoint user and item ID spaces across markets, removing the shared anchors that…
arXiv:2609.29735v1 Announce Type: cross Abstract: Long-horizon tasks require preserving and later recovering cross-session evidence under a bounded, query-blind memory budget. Existing compression can discard…
arXiv:2609.29983v1 Announce Type: new Abstract: Semantic IDs (SIDs) encode each catalog item as a short token sequence, enabling generative recommenders to predict the next item autoregressively. Reasoning-enhanced…
42 items available
