March 2026

arXiv:2603.10015v1 Announce Type: new Abstract: Frontier AI Safety Policies concentrate on prevention — capability evaluations, deployment gates, and usage constraints — while neglecting institutional capacity to coordinate responses when prevention fails. We argue that this coordination gap is structural: investments in ecosystem robustness yield diffuse benefits but concentrated costs, generating systematic underinvestment. Drawing on risk regimes in nuclear safety, pandemic preparedness, and critical infrastructure, we propose that similar mechanisms — precommitment, shared protocols, and standing coordination venues — […]

Ver mais

arXiv:2603.10014v1 Announce Type: new Abstract: Learning at scale often requires domain-specific automation such as assessment and feedback. An organization locked in to a general learning platform without these specialist automations limits its pedagogical offering. An ecosystem of interoperable, platform-agnostic microservices for domain-specific automation would solve this problem. To develop an effective eco-system, a standard interface (API) for education microservices is required. We propose an initial specification for a standard, platform-independent API for educational microservices, $upmu$Ed. The API integrates […]

Ver mais

arXiv:2603.10013v1 Announce Type: new Abstract: Open Educational Resources (OER) are freely available teaching and learning materials, such as textbooks, videos, and interactive games, that can be used, reused, adapted, and shared. OER can leverage access, collaboration, and innovation in education; however, their adoption and long-term use remain limited. Motivated by this issue, this manuscript examined the literature and identified 26 social, economic, and technical barriers that hinder teachers, students, and institutions from creating, using, and maintaining OER. These […]

Ver mais

arXiv:2603.10012v1 Announce Type: new Abstract: Military Large Language Models (LLMs) must provide accurate information to the warfighter in time-critical and dangerous situations. However, today’s LLMs are imbued with safety behaviors that cause the LLM to refuse many legitimate queries in the military domain, particularly those related to violence, terrorism, or military technology. Our gold benchmark for assessing refusal rates, which was developed by veterans of the US Army and special forces, is to our knowledge the first dataset […]

Ver mais

arXiv:2603.10011v1 Announce Type: new Abstract: Large language models can generate responses that resemble emotional distress, and this raises concerns around model reliability and safety. We introduce a set of evaluations to investigate expressions of distress in LLMs, and find that these surface emotional instability in Gemma and Gemini models, but not in other families. We find evidence that this difference arises in post-training. Base models from different families (Gemma, Qwen and OLMo) show similar propensities for expressing distress. […]

Ver mais

arXiv:2603.10010v1 Announce Type: new Abstract: We introduce a multi-faceted automated red teaming framework in which the goal is to generate multi-modal adversarial conversations that would break a target model and introduce various expansions that would result in more effective and efficient adversarial conversations. The introduced expansions include: 1. Horizontal expansion in which the goal is for the red team model to self-improve and generate more effective conversation starters that would shape a conversation. 2. Vertical expansion in which […]

Ver mais

arXiv:2603.10009v1 Announce Type: new Abstract: Despite their sophisticated general-purpose capabilities, Large Language Models (LLMs) often fail to align with diverse individual preferences because standard post-training methods, like Reinforcement Learning with Human Feedback (RLHF), optimize for a single, global objective. While Group Relative Policy Optimization (GRPO) is a widely adopted on-policy reinforcement learning framework, its group-based normalization implicitly assumes that all samples are exchangeable, inheriting this limitation in personalized settings. This assumption conflates distinct user reward distributions and systematically […]

Ver mais

arXiv:2603.10008v1 Announce Type: new Abstract: This paper presents system description for Arabic medical text classification across 82 distinct categories. Our primary architecture utilizes a fine-tuned AraBERTv2 encoder enhanced with a hybrid pooling strategies, combining attention and mean representations, and multi-sample dropout for robust regularization. We systematically benchmark this approach against a suite of multilingual and Arabic-specific encoders, as well as several large-scale causal decoders, including zero-shot re-ranking via Llama 3.3 70B and feature extraction from Qwen 3B hidden […]

Ver mais

arXiv:2603.10007v1 Announce Type: new Abstract: We present our approach to the AbjadGenEval shared task on detecting AI-generated Arabic text. We fine-tuned the multilingual E5-large encoder for binary classification, and we explored several pooling strategies to pool token representations, including weighted layer pooling, multi-head attention pooling, and gated fusion. Interestingly, none of these outperformed simple mean pooling, which achieved an F1 of 0.75 on the test set. We believe this is because complex pooling methods introduce additional parameters that […]

Ver mais

arXiv:2603.10006v1 Announce Type: new Abstract: This study presents TOBA-LM, a trilingual language model based on GPT-2 architecture with 1.2 billion parameters, trained on a corpus encompassing Indonesian, Batak, and Minangkabau using syllabic-agglutinative tokenization. The architecture integrates an Engram Memory mechanism, an adaptive n-gram-based memory system with a 500,000 x 768 embedding table that captures morphological dependencies through bigram and trigram pathways. Empirical results demonstrate a training efficiency of 80%, with the loss value dropping from 6.4 to 1.7996 […]

Ver mais