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.
38 articles · 4 sources · 38 papers ·
Top topics: AI Research · AI · Information Retrieval
arXiv:2610.30167v1 Announce Type: cross Abstract: Optimizing Information Retrieval (IR) pipelines for Retrieval-Augmented Generation (RAG) requires jointly selecting structural components and numerical hyperparameters…
arXiv:2610.31011v1 Announce Type: new Abstract: Formalized mathematics libraries such as Lean's \texttt{mathlib} provide machine-verifiable representations of mathematical knowledge, including definitions, theorems, and…
arXiv:2610.30359v1 Announce Type: new Abstract: Fairness-aware recommender systems often encode one fairness objective during training or apply a fixed re-ranking rule after scoring. In deployment, however, the…
arXiv:2610.30181v1 Announce Type: new Abstract: Despite substantial progress in Deep Search agents, their ability to conduct end-to-end research in real-world open Web environments remains insufficiently evaluated.…
arXiv:2610.30423v1 Announce Type: new Abstract: CTR, MRR, and behavioral NDCG assume the user sees ranked results and acts on them. In an agentic assistant, a generation layer consumes retrieval output first, and that…
arXiv:2610.30175v1 Announce Type: new Abstract: We introduce FormBench, a platform for testing the ability of models to retrieve precise chemical information from technical documents. FormBench contains 55,352 queries…
arXiv:2610.30664v1 Announce Type: cross Abstract: Large language models increasingly act as controllers in structured decision pipelines, yet their decisions are still executed by autoregressive text decoding.…
arXiv:2609.22486v2 Announce Type: replace-cross Abstract: Large language models (LLMs) increasingly ground their answers in proprietary data and live web content through both single-shot retrieval-augmented generation…
arXiv:2610.30365v1 Announce Type: cross Abstract: Web-searching Large Language Models (LLMs) have changed how users seek online information: instead of sifting through ranked lists of links, users read synthesized…
arXiv:2405.13795v5 Announce Type: replace Abstract: Approximate nearest neighbour (ANN) search has become a central task in modern data-intensive applications, particularly when operating on large-scale, heterogeneous,…
arXiv:2610.30425v1 Announce Type: new Abstract: Learned sparse retrieval (LSR) has recently gained traction in the information retrieval community for the ability to combine the generalization capabilities of neural…
arXiv:2610.30843v1 Announce Type: cross Abstract: We introduce Lean Finder V2, a semantic search framework for Mathlib that disambiguates user queries through complementary model-level adversarial training and…
arXiv:2610.30611v1 Announce Type: cross Abstract: Scaling large language models has substantially improved linguistic fluency, yet reliable autonomous agents require more than fluent generation. In multi-turn inference,…
arXiv:2610.30177v1 Announce Type: new Abstract: Visual document retrieval relies on rich multi-vector representations to capture fine-grained evidence in document pages, but encoding and matching these representations…
arXiv:2610.30941v1 Announce Type: new Abstract: General-purpose embeddings trained on profile similarity often misrank candidates in professional networks, where relevance is inherently complementary rather than…
arXiv:2608.13384v2 Announce Type: replace Abstract: Unstructured documents constitute the majority of enterprise and web data. With the rapid development of large language models(LLMs), researchers have started to build…
arXiv:2607.26621v4 Announce Type: replace Abstract: Large language models (LLMs) have demonstrated strong reasoning capabilities, motivating their adoption as backbones for foundation recommendation models (FRMs).…
arXiv:2610.30710v1 Announce Type: new Abstract: Over-representation analysis (ORA) is widely used to interpret gene-expression studies, but its outputs are often fragmented across gene-set databases and presented as…
arXiv:2610.31385v1 Announce Type: cross Abstract: Visual document understanding is essential for acquiring knowledge from visually rich documents and is attracting growing research interest. Existing surveys emphasize…
arXiv:2605.29507v2 Announce Type: replace-cross Abstract: Dense retrieval enables effective semantic matching, yet the semantic factors underlying its relevance scores remain opaque. Sparse autoencoders (SAEs) support…
Showing 1 day · 38 items available
