无需训练，基于离散小波变换的LLM文本检测新框架，刷新零样本检测效率。
arXiv:2607.22026v1 Announce Type: new Abstract: Detecting LLM-generated text remains challenging under zero-shot and training-free conditions, especia…
100%由LLM生成的IDE，专为LLM智能体驱动设计，强调性能与隐私，反潮流中的独特产物。
I want to be very upfront: this IDE's code is 100% generated by LLMs supervised by me, I am not hiding this fact. This submission was written by a hum…
用进化策略搜索提示词嵌入，兼顾生成质量与多样性，让LLM输出更富变化。
arXiv:2605.09781v2 Announce Type: replace-cross Abstract: Large Language Models exhibit mode collapse, producing homogeneous outputs that fail to expl…
全面综述LLM生成数据的质量与可信度评估方法，涵盖框架、指标与挑战，是相关研究者的必读参考。
arXiv:2601.17717v3 Announce Type: replace Abstract: Large Language Models (LLMs) have emerged as powerful tools for generating data across various mod…
分析了2500万条评论，揭示读者如何识别和指责AI生成内容，以及反AI态度的演变
arXiv:2606.12073v1 Announce Type: cross Abstract: Generative AI has made fluent prose cheap to produce, breaking the old promise to readers that good …
让大模型生成时真正理解语义，跳出传统词元预测，论文提出Projectional Decoding新方法
arXiv:2605.30054v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used to generate software artifacts across many softwa…
多语言大模型文本检测新方案，针对真实场景打造更可靠识别系统
arXiv:2605.15518v1 Announce Type: new Abstract: The effective detection and governance of Large Language Model (LLM) generated content has become incr…