Kavli Affiliate: Jia Liu | First 5 Authors: Jia Liu, Jie Shuai, , , | Summary: Current prompting approach for language model inference mainly rely on Language Model’s (LLM) autonomous exploration of reasoning paths, confronts an inevitable retracing operation when erroneous routes are encountered. This is followed by the pursuit of alternative reasoning paths. However, […]
Continue.. SMoT: Think in State Machine