Quality follows upgrading
All Articles
arXiv:2603.12698v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) is a promising approach for improving code generation in large language models, but its …
arXiv:2603.12754v1 Announce Type: new Abstract: We present a method for learning large-scale, broad-coverage construction grammars from corpora of language use. Starting from utterances annotated with …
arXiv:2603.12768v1 Announce Type: new Abstract: As Large Language Models (LLMs) becomes a popular source for religious knowledge, it is important to know if it treats …
arXiv:2603.12795v1 Announce Type: new Abstract: Reward models (RMs) are critical components of alignment pipelines, yet they exhibit biases toward superficial stylistic cues, preferring better-presented responses …
arXiv:2603.12823v1 Announce Type: new Abstract: Computer Use Agents (CUAs) translate natural-language instructions into Graphical User Interface (GUI) actions such as clicks, keystrokes, and scrolls by …
arXiv:2603.12826v1 Announce Type: new Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) significantly enhances the reasoning capabilities of Large Language Models. When applied to RLVR, Multiple-Choice …
arXiv:2603.12872v1 Announce Type: new Abstract: This paper reports on the development of a leaderboard of Open Large Language Models (LLM) for European Portuguese (PT-PT), and …
arXiv:2603.12906v1 Announce Type: new Abstract: Research on developmentally plausible language models has largely focused on English, leaving open questions about multilingual settings. We present a …
arXiv:2603.12920v1 Announce Type: new Abstract: Cyberbullying on social media is inherently multilingual and multi-faceted, where abusive behaviors often overlap across multiple categories. Existing methods are …
arXiv:2603.12932v1 Announce Type: new Abstract: Adapting Large Language Models (LLMs) to specialized domains requires high-quality instruction tuning datasets, which are expensive to create through human …
arXiv:2603.12963v1 Announce Type: new Abstract: The widespread adoption of reinforcement learning-based alignment highlights the growing importance of reward models. Various benchmarks have been built to …
arXiv:2603.12983v1 Announce Type: new Abstract: Error Span Detection (ESD) is a crucial subtask in Machine Translation (MT) evaluation, aiming to identify the location and severity …