Scientific Knowledge-driven Decoding Constraints Improving the Reliability of LLMs

ArXi:2604.06603v1 Announce Type: new Large language models (LLMs) have shown strong knowledge reserves and task-solving capabilities, but still face the challenge of severe hallucination, hindering their practical application. Though scientific theories and rules can efficiently direct the behaviors of human manipulators, LLMs still do not utilize these highly-condensed knowledge sufficiently through