February 2026

arXiv:2602.20170v1 Announce Type: new Abstract: Existing red-teaming benchmarks, when adapted to new languages via direct translation, fail to capture socio-technical vulnerabilities rooted in local culture and law, creating a critical blind spot in LLM safety evaluation. To address this gap, we introduce CAGE (Culturally Adaptive Generation), a framework that systematically adapts the adversarial intent of proven red-teaming prompts to new cultural contexts. At the core of CAGE is the Semantic Mold, a novel approach that disentangles a prompt’s […]

Ver mais

arXiv:2602.20169v1 Announce Type: new Abstract: This Article examines the circumstances in which AI-generated outputs remain linked to their creators and the points at which they lose that connection, whether through accident, deliberate design, or emergent behavior. In cases where AI is traceable to an originator, accession doctrine provides an efficient means of assigning ownership, preserving investment incentives while maintaining accountability. When AI becomes untraceable — whether through carelessness, deliberate obfuscation, or emergent behavior — first possession rules can […]

Ver mais

arXiv:2602.20168v1 Announce Type: new Abstract: Emergency triage decisions are made under severe information constraints, yet most data-driven deterioration models are evaluated using signals unavailable during initial assessment. We present a leakage-aware benchmarking framework for early deterioration prediction that evaluates model performance under realistic, time-limited sensing conditions. Using a patient-deduplicated cohort derived from MIMIC-IV-ED, we compare hospital-rich triage with a vitals-only, MCI-like setting, restricting inputs to information available within the first hour of presentation. Across multiple modeling approaches, predictive […]

Ver mais

arXiv:2602.20167v1 Announce Type: new Abstract: Teaching assembly programming is a fundamental component of undergraduate computer science education, yet many students struggle with its abstract and low-level concepts. Existing learning tools, such as simulators and visualisers, support understanding by exposing machine states. However, they often limit students to passive observation and provide few opportunities for meaningful interaction. To address these limitations, we introduce Playsemble, a gamified learning system that transforms assembly instructions into interactive, game-like tasks in which students […]

Ver mais

arXiv:2602.20166v1 Announce Type: new Abstract: In many applications involving intelligent agents, the overwhelming volume of alerts (mostly false) generated by the agents may desensitize users and cause them to overlook critical issues, leading to the so-called ”alert fatigue”. A common strategy is to train a reflection model as a filter to intercept false alerts with labelled data collected from user verification feedback. However, a key challenge is the noisy nature of such data as it is often collected […]

Ver mais

arXiv:2602.20165v1 Announce Type: new Abstract: Contemporary high-density mapping techniques and preoperative CT/MRI remain time and resource intensive in localizing arrhythmias. AI has been validated as a clinical decision aid in providing accurate, rapid real-time analysis of echocardiographic images. Building on this, we propose an AI-enabled framework that leverages intracardiac echocardiography (ICE), a routine part of electrophysiology procedures, to guide clinicians toward areas of arrhythmogenesis and potentially reduce procedural time. Arrhythmia source localization is formulated as a three-class classification […]

Ver mais

arXiv:2602.20164v1 Announce Type: new Abstract: Knowledge distillation offers a transformative pathway to developing powerful, yet efficient, small language models (SLMs) suitable for resource-constrained environments. In this paper, we benchmark the performance and computational cost of distilled models against their vanilla and proprietary counterparts, providing a quantitative analysis of their efficiency. Our results demonstrate that distillation creates a superior performance-tocompute curve. We find that creating a distilled 8B model is over 2,000 times more compute-efficient than training its vanilla […]

Ver mais

arXiv:2602.20163v1 Announce Type: new Abstract: Aphasia is an acquired language disorder caused by injury to the regions of the brain that are responsible for language. Aphasia may impair the use and comprehension of written and spoken language. The Western Aphasia Battery-Revised (WAB-R) is an assessment tool administered by speech-language pathologists (SLPs) to evaluate the aphasia type and severity. Because the WAB-R measures isolated linguistic skills, there has been growing interest in the assessment of discourse production as a […]

Ver mais

arXiv:2602.20162v1 Announce Type: new Abstract: Catastrophic forgetting remains a major challenge when fine-tuning large language models (LLMs) on narrow, task-specific data, often degrading their general knowledge and reasoning abilities. We propose SA-SFT, a lightweight self-augmentation routine in which an LLM generates self-dialogues prior to fine-tuning, and the resulting self-authored data are mixed with task data without modifying optimization or training schedules. Despite requiring no external data or additional tuning, SA-SFT consistently mitigates catastrophic forgetting while improving in-domain performance. […]

Ver mais

Checking agent outputs isn’t enough. The real failures hide in trajectories: which tools got called, in what order, with what inputs. This article walks through a pattern for building evals when you don’t have production data yet. You define the dimensions your agent varies along, generate structured tuples across them, and turn those into natural-language test queries. Run them, read the traces, write down what broke. Those notes become goals that shape the next batch of queries. Repeat […]

Ver mais