Quality follows upgrading
Academic
arXiv:2603.22404v1 Announce Type: new Abstract: Consider a market of competing model providers selling query access to models with varying costs and capabilities. Customers submit problem …
arXiv:2603.22576v1 Announce Type: new Abstract: We introduce CAPITU, a benchmark for evaluating instruction-following capabilities of Large Language Models (LLMs) in Brazilian Portuguese. Unlike existing benchmarks …
arXiv:2603.22497v1 Announce Type: new Abstract: Where there is growing interest in in-context language learning (ICLL) for unseen languages with large language models, such languages usually …
arXiv:2603.22829v1 Announce Type: new Abstract: With the rapid development and widespread application of Large Language Models (LLMs), their potential safety risks have attracted widespread attention. …
arXiv:2603.22453v1 Announce Type: new Abstract: Community Notes have emerged as an effective crowd-sourced mechanism for combating online deception on social media platforms. However, its reliance …
arXiv:2603.22767v1 Announce Type: new Abstract: Observational studies can yield clinically actionable evidence at scale, but executing them on real-world databases is open-ended and requires coherent …
arXiv:2603.22777v1 Announce Type: new Abstract: Agricultural pest management increasingly relies on timely and accurate access to expert knowledge, yet high quality labeled data and continuous …
arXiv:2603.23114v1 Announce Type: new Abstract: A human's moral decision depends heavily on the context. Yet research on LLM morality has largely studied fixed scenarios. We …
arXiv:2603.22978v1 Announce Type: new Abstract: In the maintenance of complex systems, fault trees are used to locate problems and provide targeted solutions. To enable fault …
arXiv:2603.23149v1 Announce Type: new Abstract: Deploying safety-critical agents requires anticipating the consequences of actions before they are executed. While world models offer a paradigm for …
arXiv:2603.22651v1 Announce Type: new Abstract: The adoption of large language models (LLMs) for structured information extraction from financial documents has accelerated rapidly, yet production deployments …
arXiv:2603.22755v1 Announce Type: new Abstract: Independently trained domain specialists can be fused post-hoc into a single model that outperforms any individual specialist, and the gain …
