Quality follows upgrading
Academic
arXiv:2603.18409v1 Announce Type: new Abstract: Current document chunking methods for Retrieval-Augmented Generation (RAG) typically linearize text. This forced linearization strips away intrinsic topological hierarchies, creating …
arXiv:2603.18411v1 Announce Type: new Abstract: Large language models (LLMs) exhibit strong reasoning capabilities but typically require expensive post-training to reach high performance. Recent test-time alignment …
arXiv:2603.18425v1 Announce Type: new Abstract: Task interference, the performance degradation caused by task switches within a single conversation, has been studied exclusively in text-only settings …
arXiv:2603.18428v1 Announce Type: new Abstract: Decoding strategies largely determine the quality of Large Language Model (LLM) outputs, yet widely used heuristics such as greedy or …
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, …
