small language model

Market shaping via digital public infrastructure for assistive technology in low- and middle-income countries

This perspective argues that market-shaping strategies should prioritise the development of shared digital infrastructure beneath the application layer; this includes representative datasets and language resources, reusable models and reference toolchains, and deployment pathways tailored to resource-constrained enviro...

Low-resource hallucination detection in LLMs on multi-task datasets via iterative pseudo-labeling using confidence thresholding and active learning

A lightweight, semi-supervised, and reproducible framework that achieves competitive performance without relying on resource-intensive models for hallucination detection across three natural language processing tasks, including machine translation, definition modeling, and paraphrase generation is presented.

Automated CEAP Classification of Venous Duplex Reports Using Multimodal Artificial Intelligence.

This study demonstrates the feasibility of automated CEAP classification from VDUS reports, and offers potential to streamline vascular services through automated triage and guideline-compliant decision making.

Memory Safety Where It Is Needed: Proof-Guided Runtime Checking in a Toolchain Small Enough to Read

Fil-C showed that C can be made memory-safe at run time by giving every pointer acapability and checking it on every access. We take its diagnostic ambitions and put themsomewhere else: in a compiler small enough for a person, or a language model, to hold inview at once, and with a different goal. Crust’s --mem-safe is...

Prevalence of unruptured intracranial aneurysms according to comorbidities, risk factors, country, and time period: a systematic review and meta-analysis.

Whether the decrease in subarachnoid haemorrhage incidence is paralleled by declines in unruptured intracranial aneurysm (UIA) prevalence is paralleled by declines in unruptured intracranial aneurysm (UIA) prevalence is investigated.

Fine-Tuning and Evaluation of LLMs

This chapter explains why fine-tuning is essential for adapting large language models (LLMs) to specialized and high-stakes domains, where general-purpose prompting may be unreliable. This chapter introduces fine-tuning as the process of updating a pretrained model with task-specific data and reviews evidence from heal...

Social Contract as a Generative Relational Process: Agency, Rule Formation, and Effective Freedom

Social-contract arguments often assign capacities, interpretations, options, and reasons to parties at a selected justificatory or bargaining stage. This analytical practice can be appropriate for its declared purpose. It can also omit two dependencies that matter for explanation and, under further premises, for normat...

When to Escalate: A Cost-Aware Belief Policy for Conversational Agents Under Hidden Intent

A conversational agent replying to inbound sales leads must choose an action before it knows the lead’s intent. It can answer, ask a qualifying question, hold, or escalate to a human, but the true buying-readiness and whether a human is actually needed are hidden. The two ways of being wrong are not equally costly. A m...

DDA: a traceable multi-agent framework for automated structure-based drug design

Results indicate that DDA provides a scalable, executable, and traceable computational framework that reduces manual coordination in structure-based automated drug discovery and delivers prioritized candidate sets with minimal human intervention.

Policy-TD: Teacher-Distilled Runtime Control for Frozen Small Language Models

A survey of edge–cloud collaborative large language models for discrete manufacturing: Architectures, technologies, and applications

HIEF: An Interpretable Evidence-Fusion Framework for Phishing Email Detection with Decomposable Decision Uncertainty and a Preliminary English–Spanish Evaluation

This work asks how far a fully interpretable detector can close the accuracy gap to an opaque text classifier while preserving per-decision explanations, and what such a detector returns that accuracy alone does not measure.