Quality follows upgrading
All Articles
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:2603.09997v1 Announce Type: cross Abstract: When OpenAI deprecated GPT-4o in early 2026, thousands of users protested under #keep4o, claiming newer models had "lost their empathy." …
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:2603.09986v1 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:2603.10661v1 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:2603.09991v1 Announce Type: cross Abstract: The rapid growth of the global poultry industry, driven by rising demand for affordable animal protein, has intensified public discourse …
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:2603.10016v1 Announce Type: cross Abstract: We investigate whether large language models (LLMs) display human-like cognitive biases, focusing on potential implications for assistance in judicial sentencing, …
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:2603.10291v1 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 …
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:2603.09980v1 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 …