# Integrating Expert Knowledge into Logical Programs via LLMs

arXiv: https://arxiv.org/abs/2502.12275 · HTML: https://mlsanity.com/paper/2502.12275/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 54 of its 79 references that are in the map.
- First posted on arXiv 17 Feb 2025.

## Placed in

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

## Builds on (most cited first, 30 of 54)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Qwen2.5-Coder Technical Report](https://mlsanity.com/paper/2409.12186/) (2024)
- [Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks](https://mlsanity.com/paper/2211.12588/) (2022)
- [Improve Mathematical Reasoning in Language Models by Automated Process Supervision](https://mlsanity.com/paper/2406.06592/) (2024)
- [Logic-LM: Empowering Large Language Models with Symbolic Solvers for Faithful Logical Reasoning](https://mlsanity.com/paper/2305.12295/) (2023)
- [Transformers as Soft Reasoners over Language](https://mlsanity.com/paper/2002.05867/) (2020)
- [LINC: A Neurosymbolic Approach for Logical Reasoning by Combining Language Models with First-Order Logic Provers](https://mlsanity.com/paper/2310.15164/) (2023)
- [Goedel-Prover: A Frontier Model for Open-Source Automated Theorem Proving](https://mlsanity.com/paper/2502.07640/) (2025)
- [Large Language Models are few(1)-shot Table Reasoners](https://mlsanity.com/paper/2210.06710/) (2022)
- [Limitations of the LLM-as-a-Judge Approach for Evaluating LLM Outputs in Expert Knowledge Tasks](https://mlsanity.com/paper/2410.20266/) (2024)
- [Faithful Logical Reasoning via Symbolic Chain-of-Thought](https://mlsanity.com/paper/2405.18357/) (2024)
- [Large Language Models Can Automatically Engineer Features for Few-Shot Tabular Learning](https://mlsanity.com/paper/2404.09491/) (2024)
- [If LLM Is the Wizard, Then Code Is the Wand: A Survey on How Code Empowers Large Language Models to Serve as Intelligent Agents](https://mlsanity.com/paper/2401.00812/) (2024)
- [Are Your LLMs Capable of Stable Reasoning?](https://mlsanity.com/paper/2412.13147/) (2024)
- [Enchanting Program Specification Synthesis by Large Language Models using Static Analysis and Program Verification](https://mlsanity.com/paper/2404.00762/) (2024)
- [Lemur: Integrating Large Language Models in Automated Program Verification](https://mlsanity.com/paper/2310.04870/) (2023)
- [Iterative Refinement of Project-Level Code Context for Precise Code Generation with Compiler Feedback](https://mlsanity.com/paper/2403.16792/) (2024)
- [A Closer Look at the Self-Verification Abilities of Large Language Models in Logical Reasoning](https://mlsanity.com/paper/2311.07954/) (2023)
- [Improving LLM Reasoning through Scaling Inference Computation with Collaborative Verification](https://mlsanity.com/paper/2410.05318/) (2024)
- [Symbol-LLM: Towards Foundational Symbol-centric Interface For Large Language Models](https://mlsanity.com/paper/2311.09278/) (2023)
- [Automatic Programming: Large Language Models and Beyond](https://mlsanity.com/paper/2405.02213/) (2024)
- [Verification and Refinement of Natural Language Explanations through LLM-Symbolic Theorem Proving](https://mlsanity.com/paper/2405.01379/) (2024)
- [DetermLR: Augmenting LLM-based Logical Reasoning from Indeterminacy to Determinacy](https://mlsanity.com/paper/2310.18659/) (2023)
- [CodeHalu: Investigating Code Hallucinations in LLMs via Execution-based Verification](https://mlsanity.com/paper/2405.00253/) (2024)
- [Beyond Accuracy: Evaluating Self-Consistency of Code Large Language Models with IdentityChain](https://mlsanity.com/paper/2310.14053/) (2023)
- [LeanReasoner: Boosting Complex Logical Reasoning with Lean](https://mlsanity.com/paper/2403.13312/) (2024)
- [ECCO: Can We Improve Model-Generated Code Efficiency Without Sacrificing Functional Correctness?](https://mlsanity.com/paper/2407.14044/) (2024)
- [RuleArena: A Benchmark for Rule-Guided Reasoning with LLMs in Real-World Scenarios](https://mlsanity.com/paper/2412.08972/) (2024)
- [Language Models can be Logical Solvers](https://mlsanity.com/paper/2311.06158/) (2023)
- [LogicAsker: Evaluating and Improving the Logical Reasoning Ability of Large Language Models](https://mlsanity.com/paper/2401.00757/) (2024)

## Built on by (most cited first, 3 of 3)

- [Adaptive LLM-Symbolic Reasoning via Dynamic Logical Solver Composition](https://mlsanity.com/paper/2510.06774/) (2025)
- [Biomedical reasoning in action: Multi-agent System for Auditable Biomedical Evidence Synthesis](https://mlsanity.com/paper/2510.05335/) (2025)
- [TreeAgent: A Generalizable Multi-Agent Framework for Automated Bias Labeling in Forestry via Compiled Expert Rules and Vision-Language Models](https://mlsanity.com/paper/2606.31976/) (2026)

## Abstract (arXiv)

This paper introduces ExKLoP, a novel framework designed to evaluate how effectively Large Language Models (LLMs) integrate expert knowledge into logical reasoning systems. This capability is especially valuable in engineering, where expert knowledge-such as manufacturer-recommended operational ranges-can be directly embedded into automated monitoring systems. By mirroring expert verification steps, tasks like range checking and constraint validation help ensure system safety and reliability. Our approach systematically evaluates LLM-generated logical rules, assessing both syntactic fluency and logical correctness in these critical validation tasks. We also explore the models' capacity for self-correction via an iterative feedback loop based on code execution outcomes. ExKLoP presents an extensible dataset comprising 130 engineering premises, 950 prompts, and corresponding validation points. It enables comprehensive benchmarking while allowing control over task complexity and scalability of experiments. We leverage the synthetic data creation methodology to conduct extensive empirical evaluation on a diverse set of LLMs including Llama3, Gemma3, Codestral and QwenCoder. The results reveal that most models generate nearly perfect syntactically correct code and exhibit strong performance in translating expert knowledge into correct code. At the same time, while most LLMs produce nearly flawless syntactic output, their ability to correctly implement logical rules varies, as does their capacity for self-improvement. Overall, ExKLoP serves as a robust evaluation platform that streamlines the selection of effective models for self-correcting systems while clearly delineating the types of errors encountered.