逐Token定位大模型谄媚行为，用归因引导精准纠偏，提升模型可靠性。
arXiv:2607.28906v1 Announce Type: new Abstract: Sycophancy refers to the tendency for large language models (LLMs) to match user beliefs at the cost o…
研究评估了Google Gemini和ChatGPT-4o在医疗诊断中的一致性、抗操纵性和上下文敏感性，揭示LLM可靠性关键挑战。
arXiv:2503.10647v2 Announce Type: replace-cross Abstract: This study evaluated the diagnostic reliability of two Large Language Models (LLMs), Google …
以隐马尔可夫模型为例，揭示从预训练大语言模型中提取可解释算法的前沿方法。
arXiv:2607.22646v1 Announce Type: cross Abstract: Large language models (LLMs) display a striking ability to predict next observations from Hidden Mar…
揭秘大模型如何被输入顺序“带偏”——这项研究深入分析了LLM偏好的脆弱性，对理解模型鲁棒性至关重要。
arXiv:2506.14092v4 Announce Type: replace Abstract: Large language models (LLMs) are increasingly deployed in decision-support systems for high-stakes…
最新研究揭示：部分大语言模型在风险决策中展现出与人类一致且稳定的风险态度，这对AI安全与行为对齐很有启发。
arXiv:2607.16197v1 Announce Type: new Abstract: As artificial intelligence systems are deployed in open-ended, high-stakes settings, a critical dimens…
LLM与深度学习融合框架，驱动智能代理守护工业物联网安全，突破传统规则监控瓶颈。
arXiv:2607.09076v1 Announce Type: new Abstract: Cyberattacks on operational technology are increasingly causing costly downtime and physical damage, e…
结合3D感知能力的LLM实现自我中心视角下的人体运动预测，ECCV 2026录用论文，AI与视觉交叉前沿。
arXiv:2607.07001v1 Announce Type: new Abstract: Anticipating human motion from an egocentric perspective is fundamental for proactive assistance in AR…
用NLP和LLM自动识别新闻中可持续发展目标的正面或负面态度，技术报告新鲜出炉
arXiv:2509.19833v4 Announce Type: replace-cross Abstract: The United Nations' Sustainable Development Goals (SDGs) provide a globally recognised frame…
不用标注数据也能精准识别漏洞？ANVIL利用LLM的异常检测新范式，突破监督学习局限
arXiv:2408.16028v4 Announce Type: replace-cross Abstract: Supervised-learning-based vulnerability detectors often fall short due to limited labelled t…
arxiv新研究：诊断并缓解长程搜索中的"上下文旋转"问题，优化AI推理过程
arXiv:2606.29718v1 Announce Type: cross Abstract: Extensive context has become the norm as Large Language Models (LLMs) are increasingly deployed in l…
一篇立场论文，直指LLM领域滥用“机器遗忘”术语，引发对模型安全与概念严谨性的反思
arXiv:2606.27379v1 Announce Type: cross Abstract: Large language models increasingly face demands to "forget" training data, knowledge, or behaviors d…
大型推理模型在跨域隐喻理解上存在对齐偏差，揭示隐喻是模型跨域误对齐的关键来源，为提升AI语义鲁棒性提供新视角。
arXiv:2601.03388v3 Announce Type: replace-cross Abstract: Earlier research has shown that metaphors influence human decision-making, raising the quest…
基于大型语言模型实现智能邮件分派，让AI自动理解邮件内容并精准路由，提升效率。
arXiv:2606.26593v1 Announce Type: new Abstract: Email communication has become an integral part of personal and professional life, but handling its va…
改进大型语言扩散模型，高效生成高质量文本，值得所有AI开发者一读的新方法。
arXiv:2606.25331v1 Announce Type: cross Abstract: Modern large language models are predominantly trained with autoregressive factorization and causal …
揭秘LLM事实检索机制：冗余、分布式、非连续的计算过程，挑战传统认知。
arXiv:2606.21345v1 Announce Type: new Abstract: Large language models (LLMs) store and recall factual knowledge, yet the precise mechanism of how enti…
提出一种开放式自我改进推理器OpenSIR，通过自博弈突破标注数据限制，有望超越人类水平推理。
arXiv:2511.00602v3 Announce Type: replace Abstract: Recent advances in large language model (LLM) reasoning through reinforcement learning rely on ann…
评估LLM在医疗场景中的操纵风险，非洲医疗实践敲响AI伦理警钟
arXiv:2606.21977v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly piloted in African healthcare contexts, raising concer…
系统性对比多种大模型黑盒不确定性估计方法，助你理解LLM可靠性与风险量化。
arXiv:2606.19868v1 Announce Type: new Abstract: Although large language models (LLMs) have shown strong capabilities across a wide range of tasks, the…
首个专测台湾法律体系的大模型评估基准，填补法律AI地域性理解空白。
arXiv:2606.18699v1 Announce Type: new Abstract: Large language models (LLMs) have shown impressive capabilities across diverse tasks, yet their perfor…
大型语言模型如何在无沟通的多智能体环境中达成隐性协调？这篇论文探索了焦点效应的关键作用。
arXiv:2601.22184v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are increasingly deployed in multi-agent settings that require …