Quality follows upgrading
Academic
arXiv:2603.09995v1 Announce Type: cross Abstract: Behavioral interview evaluation using large language models presents unique challenges that require structured assessment, realistic interviewer behavior simulation, and pedagogical …
arXiv:2603.09988v1 Announce Type: cross Abstract: Mechanistic interpretability identifies internal circuits responsible for model behaviors, yet translating these findings into human-understandable explanations remains an open problem. …
arXiv:2603.09989v1 Announce Type: cross Abstract: We introduce the System Hallucination Scale (SHS), a lightweight and human-centered measurement instrument for assessing hallucination-related behavior in large language …
arXiv:2603.09999v1 Announce Type: cross Abstract: This paper presents the design and validation of a retrieval-based assistant that supports safety assessment, certification activities, and regulatory compliance …
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:2603.10588v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) has achieved remarkable success in logical reasoning tasks, yet whether large language model (LLM) …
arXiv:2603.10002v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly tasked with producing and manipulating structured artifacts. We consider the task of end-to-end spreadsheet …
arXiv:2603.09996v1 Announce Type: cross Abstract: The integration of large language models (LLMs) into educational processes introduces significant constraints regarding data privacy and reliability, particularly in …
arXiv:2603.10005v1 Announce Type: cross Abstract: Many Automatic Speech Recognition (ASR) applications require streaming processing of the audio data. In streaming mode, ASR systems need to …
arXiv:2603.09987v1 Announce Type: cross Abstract: Feature Transformation (FT) is a core data-centric AI task that improves feature space quality to advance downstream predictive performance. However, …
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:2603.10600v1 Announce Type: new Abstract: LLM-powered agents face a persistent challenge: learning from their execution experiences to improve future performance. While agents can successfully complete …