Quality follows upgrading
Academic
arXiv:2604.00795v1 Announce Type: new Abstract: We propose the Preference Guided Iterated Pareto Referent Optimisation (PG-IPRO) for urban route planning for people with different accessibility requirements …
arXiv:2604.00011v1 Announce Type: cross Abstract: The growing prominence of large language models (LLMs) in daily life has heightened concerns that LLMs exhibit many of the …
arXiv:2604.00594v1 Announce Type: new Abstract: As the focus in LLM-based coding shifts from static single-step code generation to multi-step agentic interaction with tools and environments, …
arXiv:2604.00445v1 Announce Type: new Abstract: Uncertainty estimation (UE) aims to detect hallucinated outputs of large language models (LLMs) to improve their reliability. However, UE metrics …
arXiv:2604.00304v1 Announce Type: new Abstract: Large language models (LLMs) exhibit strong reasoning and conversational abilities, but ensuring reliable behavior in multi-turn interactions remains challenging. In …
arXiv:2604.01613v1 Announce Type: new Abstract: In reinforcement learning (RL), temporal difference (TD) errors are widely adopted for optimizing value and policy functions. However, since the …
arXiv:2604.00890v1 Announce Type: new Abstract: Geometric Problem Solving (GPS) remains at the heart of enhancing mathematical reasoning in large language models because it requires the …
arXiv:2604.01108v1 Announce Type: new Abstract: Evaluating the ethical robustness of large language models (LLMs) deployed in software systems remains challenging, particularly under sustained adversarial user …
arXiv:2604.01506v1 Announce Type: new Abstract: Long-tailed classification, where a small number of frequent classes dominate many rare ones, remains challenging because models systematically favor frequent …
arXiv:2604.01601v1 Announce Type: new Abstract: We investigate training strategies that co-develop in-context learning (ICL) and in-weights learning (IWL), and the ability to switch between them …
arXiv:2604.00610v1 Announce Type: new Abstract: Despite extensions to speech inputs, effectively leveraging the rich knowledge and contextual understanding of large language models (LLMs) in automatic …
arXiv:2604.01683v1 Announce Type: new Abstract: Standard scaled dot-product attention computes scores from static, independent projections of the input. We show that evolving queries and keys …