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.
34 articles · 3 sources · 34 papers ·
Top topics: AI Research · AI · Information Retrieval
arXiv:2609.27155v1 Announce Type: cross Abstract: With recent advancements in large language models (LLMs) and LLM-based agents, these agents are becoming increasingly autonomous and gaining broader access to act on…
arXiv:2609.28002v1 Announce Type: cross Abstract: This paper presents an LLM-assisted workflow for visualizing structural differences in evolving software require- ments. Implemented in the OntologyWeb environment, the…
arXiv:2609.28437v1 Announce Type: cross Abstract: Online information is increasingly consumed in video format. Much of this comes in the form of *raw video*: continuous footage taken on a cell phone, with a hand-held…
arXiv:2601.09562v3 Announce Type: replace Abstract: Existing retrieval benchmarks primarily consist of text-based queries where keyword or semantic matching is usually sufficient. Many real-world queries contain…
arXiv:2601.15294v3 Announce Type: replace-cross Abstract: Dependency graphs that show how definitions, theorems, and proofs relate to each other are valuable for understanding the structure of mathematical texts.…
arXiv:2609.27213v1 Announce Type: new Abstract: Open-ended queries in modern Retrieval-Augmented Generation (RAG) are increasingly "diffuse," requiring a large set of documents to be assembled into a finite LLM context…
arXiv:2609.27009v1 Announce Type: cross Abstract: Large language models are increasingly applied to high-risk domains such as law, yet complex legal reasoning remains limited by two structural challenges. First,…
arXiv:2609.26921v1 Announce Type: new Abstract: Traditional e-commerce search platforms rely heavily on inverted indices and token-level lexical matching algorithms (e.g., BM25 and TF-IDF), which frequently fail on…
arXiv:2609.27359v1 Announce Type: cross Abstract: Vietnam's Personal Data Protection Law (Law No. 91/2025/QH15) and Decree No. 356/2025/ND-CP, effective January 1, 2026, require organizations to establish and maintain…
arXiv:2609.26976v1 Announce Type: cross Abstract: Learned context planning selects evidence atoms before an answer model reasons over them. We test whether this learned selection improves long-context multiple-choice QA…
arXiv:2609.27688v1 Announce Type: new Abstract: Visual document retrieval (VDR) systems depend on page embeddings computed before deployment, which makes adaptation difficult when encoder parameters or corpus…
arXiv:2609.27814v1 Announce Type: cross Abstract: In statutory question answering, every claim must be traceable to evidence, not merely relevant, since unverifiable labour-rights answers carry serious legal…
arXiv:2512.11490v2 Announce Type: replace-cross Abstract: Satellite imagery differs from natural images in viewpoint, resolution, scale variation, and the prevalence of small objects -- demanding both region-level…
arXiv:2609.27367v1 Announce Type: cross Abstract: Verifying outsourced language-model inference requires a precisely identified computation and an audit whose cost a service can afford. We present Sampled Layerwise…
arXiv:2609.28108v1 Announce Type: new Abstract: While hypergraph-based Retrieval-Augmented Generation (RAG) effectively captures higher-order multi-entity correlations, existing paradigms treat extracted hyperedges as…
arXiv:2511.04541v2 Announce Type: replace Abstract: Slate recommender systems (RecSys) present users with ordered sets of interacting items (e.g., playlists). We investigate whether large language models (LLMs) can…
arXiv:2609.27844v1 Announce Type: cross Abstract: Claim denial management costs U.S. healthcare approximately $260 billion annually in administrative overhead. Large Language Models (LLMs) and Retrieval-Augmented…
arXiv:2609.26977v1 Announce Type: new Abstract: Offline top-k evaluation often ranks one held-out relevant item together with sampled negatives. When several candidates receive exactly the same score, the tie-breaking…
arXiv:2609.28383v1 Announce Type: new Abstract: Watch time is the primary engagement signal in short video feeds, and its prediction directly affects ranking and exposure. Existing methods improve watch time prediction…
arXiv:2609.23354v3 Announce Type: replace Abstract: Traditional Web search follows a human-facing paradigm in which users inspect ranked documents and synthesize information themselves. In AI Search, retrieved documents…
Showing 1 day · 34 items available
