一项被KDD 2026接收的新方法，通过形式化与校准探针精准映射大模型推理能力，揭示LLM深层认知图谱。
arXiv:2603.05290v2 Announce Type: replace Abstract: Large language models (LLMs) achieve promising performance, yet their ability to reason remains po…
openclaw 是一款开源 CI/CD 工具链，提供日志限制、响应体监控、就绪探针和制品检查，助力高效 DevOps 流程。
2026.5.31 Highlights Agents and CLI-backed runtimes recover more cleanly from interrupted tool calls, stale session bindings, compaction handoffs, and…
精准揭示LLM幻觉根源，区分两种违规类型，为模型知识归因与纠错提供新思路。
arXiv:2602.22787v2 Announce Type: replace-cross Abstract: Large language model (LLM) hallucinations, meaning fluent but factually incorrect generation…
大模型能编码因果方向，但输出却返回反常识答案，揭示隐藏状态与表达的不匹配。
arXiv:2605.25891v1 Announce Type: cross Abstract: We find a mismatch between what large language models encode about a causal question and what they a…
针对LLM越狱新方法，采用自适应探针引导，克服了传统对比引导的偏差和手动调参局限，提升鲁棒性与有效性。
arXiv:2605.20286v1 Announce Type: cross Abstract: Recent work has demonstrated the potential of contrastive steering for jailbreaking Large Language M…
提出“数据探针”新范式，从因果层面揭示数据如何影响大模型性能，AI研究必读。
arXiv:2605.18801v1 Announce Type: cross Abstract: Data is fundamental to large language models (LLMs). However, understanding of what makes certain da…
提出用嵌入距离与方向编码实体关系的简单神经代码，线性探针成功解码LLM内部语义结构
arXiv:2605.14125v2 Announce Type: replace Abstract: How do artificial neural networks bind concepts to form complex semantic structures? Here, we prop…
论文探索线性探针在角色坐标下对LLM有害行为的泛化监测，直指战略欺骗与沙袋问题。
arXiv:2605.09391v2 Announce Type: replace Abstract: It is becoming increasingly necessary to have monitors check for harmful behaviors during language…