Towards Unifying Logical Entailment and Statistical Estimation
On the map: LLM reasoning → Reasoning benchmarks and evaluation
Abstract (arXiv)
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.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning. Builds on 0 of its 13 references that are in the map. First posted on arXiv 27 Feb 2022.
Builds on
0 of 13 references.
No references here yet.
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2023A Simple Generative Model of Logical Reasoning and Statistical Learning
- 2025Inference of Abstraction for Grounded Predicate Logic
- 2025Can Large Language Models Learn Formal Logic? A Data-Driven Training and Evaluation Framework
- 2022Towards Unifying Perceptual Reasoning and Logical Reasoning
- 2022Selection-Inference: Exploiting Large Language Models for Interpretable Logical Reasoning
- 2024Inference of Abstraction for a Unified Account of Symbolic Reasoning from Data
- 2024The Quantified Boolean Bayesian Network: Theory and Experiments with a Logical Graphical Model
- 2023Formal Proofs as Structured Explanations: Proposing Several Tasks on Explainable Natural Language Inference