Towards Unifying Logical Entailment and Statistical Estimation
원문 초록
This paper gives a generative model of the interpretation of formal logic for data-driven logical reasoning. The key idea is to represent the interpretation as likelihood of a formula being true given a model of formal logic. Using the likelihood, Bayes' theorem gives the posterior of the model being the case given the formula. The posterior represents an inverse interpretation of formal logic that seeks models making the formula true. The likelihood and posterior cause Bayesian learning that gives the probability of the conclusion being true in the models where all the premises are true. This paper looks at statistical and logical properties of the Bayesian learning. It is shown that the generative model is a unified theory of several different types of reasoning in logic and statistics.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Are LLMs Reliable Translators of Logical Reasoning Across Lexically Diversified Contexts?
Enhancing Reasoning Capabilities of LLMs via Principled Synthetic Logic Corpus
Automating Mathematical Proof Generation Using Large Language Model Agents and Knowledge Graphs
Formal Logic-guided Robust Federated Learning against Poisoning Attacks
Boosting Deductive Reasoning with Step Signals In RLHF
ProSLM : A Prolog Synergized Language Model for explainable Domain Specific Knowledge Based Question Answering
토론
이 논문과 연결된 포럼 글이 아직 없습니다.