Quality follows upgrading
All Articles
arXiv:2603.18446v1 Announce Type: new Abstract: Long-context inference remains challenging for large language models due to attention dilution and out-of-distribution degradation. Context selection mitigates this limitation …
arXiv:2603.18469v1 Announce Type: new Abstract: We introduce GAIN (Goal-Aligned Decision-Making under Imperfect Norms), a benchmark designed to evaluate how large language models (LLMs) balance adherence …
arXiv:2603.18474v1 Announce Type: new Abstract: Precise behavioral control of large language models (LLMs) is critical for complex applications. However, existing methods often incur high training …
arXiv:2603.18482v1 Announce Type: new Abstract: Standard decoding strategies for text generation, including top-k, nucleus sampling, and contrastive search, select tokens based on likelihood, restricting selection …
arXiv:2603.18489v1 Announce Type: new Abstract: Diffusion-based large language models (dLLMs) rely on bidirectional attention, which prevents lossless KV caching and requires a full forward pass …
arXiv:2603.18530v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used for high-stakes decisions, yet their susceptibility to spurious features remains poorly characterized. We …
arXiv:2603.18557v1 Announce Type: new Abstract: As large language models are increasingly deployed across diverse real-world applications, extending automated evaluation beyond English has become a critical …
arXiv:2603.18579v1 Announce Type: new Abstract: Evaluating whether explanations faithfully reflect a model's reasoning remains an open problem. Existing benchmarks use single interventions without statistical testing, …
arXiv:2603.18593v1 Announce Type: new Abstract: We propose a method that represents language models by log-likelihood vectors over prompt-response pairs and constructs model maps for comparing …
arXiv:2603.18611v1 Announce Type: new Abstract: Advances in social media data dissemination enable the provision of real-time information during a crisis. The information comes from different …
arXiv:2603.18612v1 Announce Type: new Abstract: We introduce DiscoPhon, a multilingual benchmark for evaluating unsupervised phoneme discovery from discrete speech units. DiscoPhon covers 6 dev and …
arXiv:2603.18620v1 Announce Type: new Abstract: We introduce Learning to Self-Evolve (LSE), a reinforcement learning framework that trains large language models (LLMs) to improve their own …