黑盒LLM分类的评分粒度短板如何破局？多置信度构造法对比，帮你选对可信判定方案。
arXiv:2606.22179v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed as black-box classifiers in pipelines that auto…
研究发现LLM中注意力值比隐藏状态更能编码句子语义，挑战传统embedding范式
arXiv:2602.01572v2 Announce Type: replace Abstract: Sentence representations are foundational to many Natural Language Processing (NLP) applications. …
系统对比解码时真实性方法在指令微调LLM上的效果，揭示不同策略的优劣与适用场景
arXiv:2606.12160v1 Announce Type: new Abstract: In this work, we introduce CHAIR (Classifier of Hallucination As ImproveR), a supervised framework for…
多光谱无人机+深度学习，哪种框架最适合水稻病害制图？这篇IGARSS论文给出系统比较。
arXiv:2606.06359v1 Announce Type: new Abstract: In this study, UAV multispectral imagery is used to segment the severity of bacterial leaf blight (BLB…
探索LLM对话界面与图形界面在工业决策任务中的优劣，为智能工具设计提供实证参考。
arXiv:2605.31224v1 Announce Type: cross Abstract: The use of Generative AI Conversational User Interfaces (CUI) as a new way to access and analyze dat…
来自ICLR2026的研究：强化学习让推理更紧凑，监督微调则让推理更发散，揭示两种范式在大模型推理上的本质差异。
arXiv:2509.21128v2 Announce Type: replace Abstract: Large language models (LLMs) are typically trained by reinforcement learning (RL) with verifiable …