Last Layer Logits to Logic: Empowering LLMs with Logic-Consistent Structured Knowledge Reasoning 事件

Last Layer Logits to Logic: Empowering LLMs with Logic-Consistent Structured Knowledge Reasoning arXiv:2511.07910v2 Announce Type: replace Abstract: Large Language Models (LLMs) achieve excellent performance in natural language reasoning tasks through pre-training on vast unstructured text, enabling them to understand the logic in natural language and generate logic-consistent responses. However, the representational differences between unstructured and structured knowledge make LLMs inherently