Quality follows upgrading
Academic
arXiv:2602.17546v1 Announce Type: new Abstract: Instruction-following language models are trained to be helpful and safe, yet their safety behavior can deteriorate under benign fine-tuning and …
arXiv:2602.17588v1 Announce Type: new Abstract: Despite rapid progress in autonomous web agents, human involvement remains essential for shaping preferences and correcting agent behavior as tasks …
arXiv:2602.17598v1 Announce Type: new Abstract: Current speech LLMs largely perform implicit ASR: on tasks solvable from a transcript, they are behaviorally and mechanistically equivalent to …
arXiv:2602.17623v1 Announce Type: new Abstract: While emerging Persian NLP benchmarks have expanded into pragmatics and politeness, they rarely distinguish between memorized cultural facts and the …
arXiv:2602.17653v1 Announce Type: new Abstract: Recent work has shown that language models (LMs) trained on synthetic corpora can exhibit typological preferences that resemble cross-linguistic regularities …
arXiv:2602.17655v1 Announce Type: new Abstract: Language Identification (LID) is an important component of many multilingual natural language processing pipelines, where it facilitates corpus curation, training …
arXiv:2602.17664v1 Announce Type: new Abstract: Diffusion Language Models (DLMs) incur high inference cost due to iterative denoising, motivating efficient pruning. Existing pruning heuristics largely inherited …
arXiv:2602.16729v1 Announce Type: cross Abstract: We systematically evaluate the quality of widely used AI safety datasets from two perspectives: in isolation and in practice. In …
arXiv:2602.16784v1 Announce Type: cross Abstract: Despite their impressive performance on a wide variety of tasks, modern language models remain susceptible to distribution shifts, exhibiting brittle …
arXiv:2602.16787v1 Announce Type: cross Abstract: Despite their strong performance on reasoning benchmarks, large language models (LLMs) have proven brittle when presented with counterfactual questions, suggesting …
arXiv:2602.16819v1 Announce Type: cross Abstract: When assessing the quality of coding agents, predominant benchmarks focus on solving single issues on GitHub, such as SWE-Bench. In …
arXiv:2602.16730v1 Announce Type: new Abstract: Accurate speed prediction is crucial for proactive traffic management to enhance traffic efficiency and safety. Existing studies have primarily relied …