Daily edition · Information Retrieval
TILens turns technical updates into a focused daily brief: official releases, trusted reporting, and practitioner analysis, deduplicated and organized by topic.
35 articles · 5 sources · 34 papers ·
Top topics: Information Retrieval · AI · AI Research
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: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.…
arXiv:2610.10091v1 Announce Type: cross Abstract: Knowledge-intensive tasks require answering many questions by reasoning about a shared corpus of artifacts (e.g., court cases, or scientific literature). As humans…
arXiv:2609.13205v2 Announce Type: replace Abstract: Sparse long-context inference requires efficient token retrieval in both prefill and decode. Existing methods often use different retrieval strategies for the two…
arXiv:2610.10124v1 Announce Type: new Abstract: Generative recommenders return a limited candidate set and may omit observed targets before reranking. A training strategy appends these missed targets to reranker…
arXiv:2610.08808v1 Announce Type: cross Abstract: Satisfiability Modulo Theories (SMT) solvers are foundational to software verification, program analysis, and compiler testing, particularly over the theory of…
arXiv:2610.09863v1 Announce Type: cross Abstract: Standard information retrieval metrics, such as mean Average Precision (mAP), assess performance one query at a time, based on how the similarities between a query and…
arXiv:2610.08200v2 Announce Type: replace Abstract: We ask whether specific attention heads, and more finely specific neurons inside those heads, are responsible for recognizing that a language model's context contains…
arXiv:2602.02624v2 Announce Type: replace-cross Abstract: Several data protection laws restrict processing that reveals political opinions, irrespective of the controller's intent. Whether recommender systems do so as a…
arXiv:2605.18850v2 Announce Type: replace-cross Abstract: We introduce KadiAssistant, a privacy-by-design AI assistant integrated into the Kadi research data ecosystem, enabling researchers to efficiently access,…
arXiv:2610.09193v1 Announce Type: cross Abstract: MemoryAgentBench's Conflict Resolution split is read as measuring "selective forgetting". We execute the benchmark's own rule - the newest statement about a fact wins -…
arXiv:2607.28263v2 Announce Type: replace Abstract: Repeated queries over shared documents repeatedly execute the same lower transformer layers. We introduce CoMem, which makes split depth j an explicit reusable-context…
arXiv:2610.09742v1 Announce Type: cross Abstract: Refereeing decisions in professional soccer remain inconsistent because referees cannot easily compare a contentious foul against similar past cases. We cast this as a…
arXiv:2610.09039v1 Announce Type: cross Abstract: Large language models can extract useful signals from heterogeneous enterprise data, but high-recall extraction often produces outputs that are duplicated, uneven in…
arXiv:2610.09724v1 Announce Type: new Abstract: Query Expansion (QE) techniques have long been widely used in Information Retrieval (IR) to address the vocabulary mismatch problem. They remain relevant in modern…
Showing 1 day · 35 items available
