针对RAG幻觉难题，提出基于归纳感知熵门控的不确定性估计新方法，直击熵基方法失效痛点。
arXiv:2603.21607v2 Announce Type: replace Abstract: While retrieval-augmented generation (RAG) significantly improves the factual reliability of LLMs,…
提出注意力动态对齐与偏好微调方法，从内部注意力演化破解多模态幻觉难题
arXiv:2606.31054v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) are critically hampered by hallucination, generating conten…
用参数化世界模型替代自由想象，切断智能体幻觉在上下文中的连锁传播，让多步规划更可靠。
arXiv:2606.27806v1 Announce Type: new Abstract: World models for language agents come in two useful forms. An agent-based world model calls an LLM API…
3D脑MRI报告生成事实性难题，用成对图文检索与文本增强巧妙破解，医学影像AI必读。
arXiv:2411.15490v2 Announce Type: replace-cross Abstract: Acute ischemic stroke (AIS) requires time-critical decision-making, where inaccurate interpr…
引入距离索引神经A*的图式推理链，兼顾首Token延迟，大幅降低医学多跳问答幻觉，值得AI医疗研发者细读。
arXiv:2606.23108v1 Announce Type: new Abstract: Hallucinations and opaque reasoning remain unacceptable failure modes for clinical LLMs. We present a …
被ICML 2026接收，提出通过幻觉拒绝采样显著提升长文本生成的可靠性，是NLP领域的重要突破。
arXiv:2606.03628v1 Announce Type: cross Abstract: Large language models (LLMs) have achieved remarkable progress in open-ended text generation, yet th…