登录
洞察 - Logically Consistent Language Models
Improving Logical Consistency of Large Language Models via Neuro-Symbolic Integration
Logically consistent large language models can be achieved by fine-tuning them using a principled neuro-symbolic reasoning approach that encourages the model to satisfy a given set of logical constraints.
Improving Logical Consistency and Factuality of Large Language Models through Probabilistic Reasoning
Large language models can be trained to be more logically consistent and factual by incorporating principled probabilistic reasoning into the training objective, without relying on external reasoning tools.
