Cool Papers · cs.CL (papers.cool) · RSS 摘要

信源：Cool Papers · cs.CL (papers.cool) · https://papers.cool/arxiv/cs.CL/feed

• Flide: Accelerating Decision Inference with Exact State Forking — Decision models such as Jev have emerged as a highly promising paradigm for LLM agent systems, providing lightweight and reliable categorical reasoning for rapid System One execut…
• DecisionRank: On-Policy Distillation for Decision-Model Rerankers — Decision models target structured tasks by directly predicting choices or scores, avoiding autoregressive decoding latency. However, transferring a generative LLM's ranking knowle…
• Subquadratic Attention with a Hierarchical Tree-Structured Indexer — The quadratic scaling of attention is a fundamental bottleneck limiting the long-context capabilities of large language models (LLMs). A variety of approaches have attempted to ci…
• RangeSWA: Training-Free Length Extrapolation for Continuous Diffusion Language Models — Continuous diffusion language models show promising potential in text generation tasks, but are prone to problems such as text repetition, semantic drift, and generation quality d…
• PersonaChatBench: Evaluating Chat Assistants with Diverse Simulated Users — Conversational assistants are expected to help people with diverse backgrounds, preferences, and communication styles. Yet evaluations centered on a single cooperative user provid…