Retrieval pipelines, vector search, chunking and reranking: how models are grounded in a corpus instead of their weights.
arXiv:2606. 27941v1 Announce Type: cross Abstract: Sparse autoencoders (SAEs) provide useful decompositions of Transformer residual streams, but their learned features are usually named post hoc rather than directly connected to the Transformer's token vocabulary.
arXiv:2604. 20920v2 Announce Type: replace Abstract: Sparse attention can reduce the cost of long-context inference, but most variants introduce new architectural components.
arXiv:2606. 27579v1 Announce Type: cross Abstract: Accurate assessment of tumor proportion score (TPS) in non-small cell lung cancer (NSCLC) is critical for treatment planning and prognosis.
arXiv:2509. 19376v2 Announce Type: replace-cross Abstract: We present a lightweight, model-agnostic temporal layer for RAG and use cybersecurity data to separate two problems that are usually conflated.
Navigating the deluge of heterogeneous medical data, from academic literature (PubMed) to clinical guidelines (Web) and private knowledge bases, remains a critical bottleneck for evidence-based medicine. While commercial black-box tools lack transparency, standard open-source RAG implementations frequently suffer from reasoning drift when handling complex, long-tail queries.
Organizations that cannot send data to a cloud API increasingly ask: how good is Text-to-SQL if the model must run on-premises on open weights, and which popular accuracy "recipes" are worth their compute? We answer with an honest, fully reproducible benchmark on the BIRD development split (n=1534, Execution Accuracy), evaluating three open model families across two generations -- Qwen2.
Telecom question answering (QA) is a challenging setting for retrieval-augmented generation (RAG): evidence is fragmented across standards, papers, encyclopedic resources, and web documents, and answers often hinge on technical tables, equations, and specialized protocol language. In low-resource subdomains, generator fine-tuning can over-specialize and degrade general capability, making query-side retriever adaptation an attractive alternative.
Positron Emission Tomography (PET) reveals brain metabolism and is clinically central to neurodegenerative disease assessment, yet existing 3D brain foundation models treat PET as generic volumetric data, missing the structured regional metabolic information that distinguishes it from structural neuroimaging. To address these limitations, we propose ReMAP-PET, a framework that moves beyond visual encoding by supervising a partially-tuned MedicalNet 3D ResNet-50 with brain regional standardized uptake value ratio (SUVR) profiles through joint regression and contrastive objectives, enabling the encoder to learn the metabolic semantics underlying PET modality.
The standard way to compare two text embeddings is cosine similarity. Scattered studies report that a different metric does better, but never pin down the geometric condition that decides when, or why.
Conformal prediction guarantees marginal coverage, but pooled calibration averages over heterogeneous regions and can mask regional undercoverage in safety-critical subgroups. We introduce Self-Organized Conformal Prediction (SOCP), a calibration scheme that discovers input-space groups with a Self-Organizing Map (SOM) and, at test time, draws a local calibration buffer from the query's best-matching unit (BMU) cell or a fixed grid neighborhood.
Open-vocabulary 3D semantic Gaussian field learning relies on multi-view 2D supervision, whose semantic targets and spatial assignments are often unreliable. Across varying viewpoints, view-dependent features cause semantic identity drift, while propagated tracker masks introduce boundary leakage and identity switches.
Retrieval-Augmented Generation (RAG) has become the standard way to ground large language models in external knowledge, yet most systems retrieve a fixed number of passages for every question regardless of its difficulty. This wastes computation on easy questions, starves hard ones, and gives no signal for when a generated answer can be trusted.
Use coding agents to power your knowledge base The post How to Build a Powerful LLM Knowledge Base appeared first on Towards Data Science .
Why memorizing for the exam doesn't mean you understand the subject The post Water Cooler Small Talk, Ep. 11: Overfitting in RAG evaluation appeared first on Towards Data Science .
Enterprise Document Intelligence [Vol. 1 #M1] - The thesis behind every architectural choice in this series The post Amplify the Expert: A Philosophy for Building Enterprise RAG appeared first on Towards Data Science .
arXiv:2606. 26986v1 Announce Type: cross Abstract: Open Relation Extraction (OpenRE) requires a model to extract unseen relations between head and tail entities from unstructured text for real-world applications.
arXiv:2606. 27201v1 Announce Type: new Abstract: Event-based Temporal Graph Neural Networks (ETGNNs) have demonstrated strong performance across a wide range of applications, including social network analysis, epidemic tracing, recommender systems, and political event forecasting.
arXiv:2606. 26179v1 Announce Type: cross Abstract: While WGS-based AMR prediction has reached high accuracy, existing models lack a mechanism to ground neural attributions in established biological pathways.
arXiv:2509. 07295v4 Announce Type: replace-cross Abstract: Unified multimodal models (UMMs) unify visual understanding and generation within a single architecture.
arXiv:2606. 26511v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) gives agents access to accumulated knowledge, but has no model of time.