# Automated Theorem Provers Help Improve Large Language Model Reasoning

arXiv: https://arxiv.org/abs/2408.03492 · HTML: https://mlsanity.com/paper/2408.03492/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 10 of its 33 references that are in the map.
- First posted on arXiv 7 Aug 2024.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)

## Builds on (most cited first, 10 of 10)

- [Gemini: A Family of Highly Capable Multimodal Models](https://mlsanity.com/paper/2312.11805/) (2023)
- [Generative Language Modeling for Automated Theorem Proving](https://mlsanity.com/paper/2009.03393/) (2020)
- [Large Legal Fictions: Profiling Legal Hallucinations in Large Language Models](https://mlsanity.com/paper/2401.01301/) (2024)
- [Are Large Language Models Really Good Logical Reasoners? A Comprehensive Evaluation and Beyond](https://mlsanity.com/paper/2306.09841/) (2023)
- [Neural Probabilistic Logic Programming in Discrete-Continuous Domains](https://mlsanity.com/paper/2303.04660/) (2023)
- [Language Models with Rationality](https://mlsanity.com/paper/2305.14250/) (2023)
- [Reliable Natural Language Understanding with Large Language Models and Answer Set Programming](https://mlsanity.com/paper/2302.03780/) (2023)
- [Certified Deductive Reasoning with Language Models](https://mlsanity.com/paper/2306.04031/) (2023)
- [DeepProbLog: Neural Probabilistic Logic Programming](https://mlsanity.com/paper/1805.10872/) (2018)
- [Bottom-Up Stratified Probabilistic Logic Programming with Fusemate](https://mlsanity.com/paper/2308.15862/) (2023)

## Built on by (most cited first, 7 of 7)

- [VERGE: Formal Refinement and Guidance Engine for Verifiable LLM Reasoning](https://mlsanity.com/paper/2601.20055/) (2026)
- [A Comparative Study of Neurosymbolic AI Approaches to Interpretable Logical Reasoning](https://mlsanity.com/paper/2508.03366/) (2025)
- [Integrating Expert Knowledge into Logical Programs via LLMs](https://mlsanity.com/paper/2502.12275/) (2025)
- [Highlighting Case Studies in LLM Literature Review of Interdisciplinary System Science](https://mlsanity.com/paper/2503.16515/) (2025)
- [Overview of AI Grading of Physics Olympiad Exams](https://mlsanity.com/paper/2505.02121/) (2025)
- [Where Reasoning Breaks: Logic-Aware Path Selection by Controlling Logical Connectives in LLMs Reasoning Chains](https://mlsanity.com/paper/2604.20564/) (2026)
- [From Solvers to Research: Large Language Model-Driven Formal Mathematics at the Research Frontier](https://mlsanity.com/paper/2607.07779/) (2026)

## Abstract (arXiv)

In this paper we demonstrate how logic programming systems and Automated first-order logic Theorem Provers (ATPs) can improve the accuracy of Large Language Models (LLMs) for logical reasoning tasks where the baseline performance is given by direct LLM solutions. We first evaluate LLM reasoning on steamroller problems using the PRONTOQA benchmark. We show how accuracy can be improved with a neuro-symbolic architecture where the LLM acts solely as a front-end for translating a given problem into a formal logic language and an automated reasoning engine is called for solving it. However, this approach critically hinges on the correctness of the LLM translation. To assess this translation correctness, we secondly define a framework of syntactic and semantic error categories. We implemented the framework and used it to identify errors that LLMs make in the benchmark domain. Based on these findings, we thirdly extended our method with capabilities for automatically correcting syntactic and semantic errors. For semantic error correction we integrate first-order logic ATPs, which is our main and novel contribution. We demonstrate that this approach reduces semantic errors significantly and further increases the accurracy of LLM logical reasoning.