新研究发现LLM事实知识在最后几层突然“结晶”，而非逐层涌现，解释了为何干预后期层能有效减少幻觉。
arXiv:2606.07978v1 Announce Type: new Abstract: Understanding where LLMs store factual knowledge is critical for hallucination mitigation. We systemat…
Chatlaw是一个基于角色对齐的专家混合架构的多智能体法律助手，能有效应对中国法律知识不足和幻觉问题，提供专业可靠的法律咨询。
arXiv:2306.16092v3 Announce Type: replace Abstract: Artificial Intelligence (AI) holds great potential in legal services, yet Large Language Models (L…
新研究用回忆式提示约束大模型知识截止时间，让回答更可靠，解决幻觉问题。
arXiv:2606.05804v1 Announce Type: new Abstract: Prompted knowledge cutoff instructs a large language model (LLM) to act as if information beyond a spe…
确定性记忆框架让对话AI不再"失忆"，21页论文详解DMF如何提升对话一致性与可控性。
arXiv:2606.03463v1 Announce Type: new Abstract: Conversational AI agents require memory systems that are both scalable and semantically coherent acros…
用语义缓存嵌套学习结合Agentic AI，巧妙缓解大模型幻觉并兼顾可持续性
arXiv:2605.29055v1 Announce Type: new Abstract: Hallucination remains a major reliability barrier for production LLM systems, particularly in multi-ag…
从视觉忽视视角切入，提出上下文偏好引导新方法，精准缓解多模态大模型幻觉问题
arXiv:2605.27993v1 Announce Type: new Abstract: Object hallucination remains a primary obstacle to the reliable deployment of Multimodal Large Languag…
系统性基准评测，专攻指令跟随大模型幻觉的检测与缓解，实用且有深度。
arXiv:2605.02443v2 Announce Type: replace Abstract: Large Language Models (LLMs) have demonstrated remarkable capabilities across diverse natural lang…