Topic - Edition
This is Part 2, continuing from “Part 1: Practical Considerations.” In Part 1, the foundational concerns were laid out. Here in Part 2, common use cases and patterns to address them with best practices are covered.…
arXiv:2602.22647v3 Announce Type: replace Abstract: Generative retrieval has emerged as a powerful paradigm for LLM-based recommendation. However, industrial recommender systems often benefit from restricting the output…
arXiv:2610.10483v1 Announce Type: cross Abstract: Sampling from a softmax distribution is a fundamental operation in machine learning, but its linear complexity in the number of items makes exact sampling impractical at…
arXiv:2610.09361v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) is widely used to ground answers in documents. For complex technical documentation, however, the primary bottleneck is often not model…
arXiv:2610.01118v2 Announce Type: replace-cross Abstract: A long-term conversational assistant must recall the right memory at the right moment, yet the memory that matters most is often not similar to what the user…
arXiv:2604.05087v4 Announce Type: replace-cross Abstract: Generative large language models (LLMs) are increasingly used as inference-time components in retrieval pipelines, for tasks such as query rewriting and document…
arXiv:2610.10441v1 Announce Type: cross Abstract: Social media systems typically display conversations among already familiar contributors, which can be predictable and one-sided. In civic discourse, this design narrows…
arXiv:2610.10170v1 Announce Type: new Abstract: Retrieval-augmented generation systems increasingly rely on document-structure treatments: structure-aligned chunking, LLM-generated chunk contexts, heading-path metadata,…
arXiv:2610.09026v1 Announce Type: cross Abstract: We present BEACON-SP, an ontology-grounded Graph Retrieval-Augmented Generation (GraphRAG) framework for clinician-facing decision support in behavioral health settings…
arXiv:2610.09041v1 Announce Type: cross Abstract: Navigable graphs can be built without searching for neighbors: partition the data, evaluate every pair inside each part, and select each point's edges from the…
arXiv:2312.11018v4 Announce Type: replace Abstract: Bundle recommendation ranks sets of related items rather than isolated items. Its central challenge is to connect user preferences, item interactions, and bundle…
arXiv:2606.27980v2 Announce Type: replace Abstract: Dense embedding rankers score documents through contextual sentence- and passage-level representations, yet listwise explanation methods often attribute rankings to…
arXiv:2610.08894v1 Announce Type: new Abstract: This dissertation presents a scalable architecture for transforming unstructured, domain-specific text into structured knowledge for retrieval and reasoning. It integrates…
arXiv:2605.29280v3 Announce Type: replace-cross Abstract: Knowledge distillation (KD) transfers a single scalar prediction from a large foundation model (FM) to compact vertical models (VMs), suffering from diminishing…
arXiv:2610.09820v1 Announce Type: new Abstract: LLMs are evolving rapidly, with newer models offering stronger capabilities. This suggests that in LLM-based relevance judging, more capable models will achieve higher…
arXiv:2610.09227v1 Announce Type: new Abstract: Mixed-precision post-training quantization needs a per-module sensitivity signal; for a text embedder the obvious one -- the retrieval quality a module costs when…
arXiv:2610.09262v1 Announce Type: new Abstract: A reader's first highlights on a page are the cheapest personal signal a reading product has. The natural plan is to suggest what similar earlier readers marked, and to…
arXiv:2607.04576v2 Announce Type: replace-cross Abstract: LLM agents now often answer questions from knowledge bases they help maintain. A common intuition says progressive disclosure should make this cheaper. Instead…
arXiv:2610.09920v1 Announce Type: new Abstract: Prevailing multi-vector visual document retrievers store each page as about a thousand patch vectors, often in vector databases run by a third party. Since no one can read…
arXiv:2604.12138v5 Announce Type: replace-cross Abstract: Retrieval-Augmented Generation (RAG) systems are built on an unexamined assumption - that queries have correct answers and retrieval should converge toward them.…
35 items available
