digitado

arXiv:2603.23513v1 Announce Type: new Abstract: Commercial AI scribes cost $99-600 per physician per month, operate as opaque systems, and do not return data to institutional infrastructure, limiting organizational control over data governance, quality improvement, and clinical workflows. We developed Berta, an open-source modular scribe platform for AI-enabled clinical documentation, and deployed a customized implementation within Alberta Health Services (AHS) integrated with their existing Snowflake AI Data Cloud infrastructure. The system combines automatic speech recognition with large language models […]

Ver mais

arXiv:2603.23512v1 Announce Type: new Abstract: We present S-Path-RAG, a semantic-aware shortest-path Retrieval-Augmented Generation framework designed to improve multi-hop question answering over large knowledge graphs. S-Path-RAG departs from one-shot, text-heavy retrieval by enumerating bounded-length, semantically weighted candidate paths using a hybrid weighted $k$-shortest, beam, and constrained random-walk strategy, learning a differentiable path scorer together with a contrastive path encoder and lightweight verifier, and injecting a compact soft mixture of selected path latents into a language model via cross-attention. The […]

Ver mais

arXiv:2603.23511v1 Announce Type: new Abstract: Document intelligence requires accurate text extraction and reliable reasoning over document content. We introduce textbf{DISCO}, a emph{Document Intelligence Suite for COmparative Evaluation}, that evaluates optical character recognition (OCR) pipelines and vision-language models (VLMs) separately on parsing and question answering across diverse document types, including handwritten text, multilingual scripts, medical forms, infographics, and multi-page documents. Our evaluation shows that performance varies substantially across tasks and document characteristics, underscoring the need for complexity-aware approach selection. […]

Ver mais

arXiv:2603.23510v1 Announce Type: new Abstract: As multimodal language models (MLMs) are increasingly used in social and collaborative settings, it is crucial to evaluate their perspective-taking abilities. Existing benchmarks largely rely on text-based vignettes or static scene understanding, leaving visuospatial perspective-taking (VPT) underexplored. We adapt two evaluation tasks from human studies: the Director Task, assessing VPT in a referential communication paradigm, and the Rotating Figure Task, probing perspective-taking across angular disparities. Across tasks, MLMs show pronounced deficits in Level […]

Ver mais

arXiv:2603.23509v1 Announce Type: new Abstract: This work identifies a critical failure mode in frontier large language models (LLMs), which we term Internal Safety Collapse (ISC): under certain task conditions, models enter a state in which they continuously generate harmful content while executing otherwise benign tasks. We introduce TVD (Task, Validator, Data), a framework that triggers ISC through domain tasks where generating harmful content is the only valid completion, and construct ISC-Bench containing 53 scenarios across 8 professional disciplines. […]

Ver mais

arXiv:2603.23508v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) is increasingly deployed in enterprise search and document-centric assistants, where responses must be grounded in long and complex source materials. In practice, verifying that generated answers faithfully reflect retrieved documents is difficult: large language models can check long contexts but are too slow and costly for interactive services, while lightweight classifiers operate within strict context limits and frequently miss evidence outside truncated passages. We present the design of a real-time […]

Ver mais

arXiv:2603.23507v1 Announce Type: new Abstract: While Masked Diffusion Language Models (MDLMs) relying on token masking and unmasking have shown promise in language modeling, their computational efficiency and generation flexibility remain constrained by the masking paradigm. In this paper, we propose Deletion-Insertion Diffusion language models (DID) that rigorously formulate token deletion and insertion as discrete diffusion processes, replacing the masking and unmasking processes in current MDLMs. DID improves training and inference efficiency by eliminating two major sources of computational […]

Ver mais

arXiv:2603.23506v1 Announce Type: new Abstract: The rapid proliferation of large language models (LLMs) in healthcare creates an urgent need for scalable and psychometrically sound evaluation methods. Conventional static benchmarks are costly to administer repeatedly, vulnerable to data contamination, and lack calibrated measurement properties for fine-grained performance tracking. We propose and validate a computerized adaptive testing (CAT) framework grounded in item response theory (IRT) for efficient assessment of standardized medical knowledge in LLMs. The study comprises a two-phase design: […]

Ver mais

arXiv:2603.23505v1 Announce Type: new Abstract: HyperFrog is an experimental post-quantum Key Encapsulation Mechanism that explores a variant of the Learning With Errors (LWE) design space in which the secret is not sampled from an independent product distribution, but is deterministically derived from discrete topological structure. The scheme embeds a voxel grid in three dimensions and uses a topology mining procedure to search for connected subgraphs with prescribed complexity, measured by cyclomatic number (high genus). The resulting structure is […]

Ver mais

arXiv:2603.23504v1 Announce Type: new Abstract: Motivated by evacuation scenarios arising in extreme events such as flooding or forest fires, we study the problem of smoothly scheduling a set of paths in graphs where connections become impassable at some point in time. A schedule is smooth if no two paths meet on an edge and the number of paths simultaneously located at a vertex does not exceed its given capacity. We study the computational complexity of the problem when […]

Ver mais