Quality follows upgrading
All Articles
arXiv:2603.09982v1 Announce Type: cross Abstract: Encoder-only transformer models remain widely used for discriminative NLP tasks, yet recent architectural advances have largely focused on English. In …
arXiv:2603.09994v1 Announce Type: cross Abstract: Compositionality is considered central to language abilities. As performant language systems, how do large language models (LLMs) do on compositional …
arXiv:2603.09992v1 Announce Type: cross Abstract: This paper presents TAMUSA-Chat, a research-oriented framework for building domain-adapted large language model conversational systems. The work addresses critical challenges …
arXiv:2603.09986v1 Announce Type: cross Abstract: Hallucinations, the tendency for large language models to provide responses with factually incorrect and unsupported claims, is a serious problem …
arXiv:2603.10359v1 Announce Type: new Abstract: Distilling reasoning capabilities from Large Reasoning Models (LRMs) into smaller models is typically constrained by the limitation of rejection sampling. …
arXiv:2603.09990v1 Announce Type: cross Abstract: In business-to-business relations, it is common to establish NonDisclosure Agreements (NDAs). However, these documents exhibit significant variation in format, structure, …
arXiv:2603.10008v1 Announce Type: cross Abstract: This paper presents system description for Arabic medical text classification across 82 distinct categories. Our primary architecture utilizes a fine-tuned …
arXiv:2603.10384v1 Announce Type: new Abstract: Evaluating LLM reliability via scalar probabilities often fails to capture the structural dynamics of reasoning. We introduce TRACED, a framework …
arXiv:2603.10661v1 Announce Type: new Abstract: We propose FAME (Formal Abstract Minimal Explanations), a new class of abductive explanations grounded in abstract interpretation. FAME is the …
arXiv:2603.10577v1 Announce Type: new Abstract: Computer-Use Agents (CUAs) are emerging as a new paradigm in human-computer interaction, enabling autonomous execution of tasks in desktop environment …
arXiv:2603.09980v1 Announce Type: cross Abstract: LLM unlearning is essential for mitigating safety, copyright, and privacy concerns in pre-trained large language models (LLMs). Compared to preference …
arXiv:2603.10291v1 Announce Type: new Abstract: The remarkable progress of vision-language models (VLMs) has enabled GUI agents to interact with computers in a human-like manner. Yet …