# Fine-tuning Large Enterprise Language Models via Ontological Reasoning

arXiv: https://arxiv.org/abs/2306.10723 · HTML: https://mlsanity.com/paper/2306.10723/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning.
- Builds on 9 of its 24 references that are in the map.
- First posted on arXiv 19 Jun 2023.

## Placed in

- LLM reasoning / [Knowledge- and tool-augmented reasoning](https://mlsanity.com/lr/knowledge-and-tool-augmented-reasoning/)

## Builds on (most cited first, 9 of 9)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Scaling Language Models: Methods, Analysis & Insights from Training Gopher](https://mlsanity.com/paper/2112.11446/) (2021)
- [BloombergGPT: A Large Language Model for Finance](https://mlsanity.com/paper/2303.17564/) (2023)
- [How Much Knowledge Can You Pack Into the Parameters of a Language Model?](https://mlsanity.com/paper/2002.08910/) (2020)
- [RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parsers](https://mlsanity.com/paper/1911.04942/) (2019)
- [SKILL: Structured Knowledge Infusion for Large Language Models](https://mlsanity.com/paper/2205.08184/) (2022)
- [Neural Machine Translating from Natural Language to SPARQL](https://mlsanity.com/paper/1906.09302/) (2019)
- [Can Pretrained Language Models (Yet) Reason Deductively?](https://mlsanity.com/paper/2210.06442/) (2022)

## Built on by (most cited first, 14 of 14)

- [Can Knowledge Graphs Reduce Hallucinations in LLMs? : A Survey](https://mlsanity.com/paper/2311.07914/) (2023)
- [T-RAG: Lessons from the LLM Trenches](https://mlsanity.com/paper/2402.07483/) (2024)
- [Solving General Natural-Language-Description Optimization Problems with Large Language Models](https://mlsanity.com/paper/2407.07924/) (2024)
- [Research Trends for the Interplay between Large Language Models and Knowledge Graphs](https://mlsanity.com/paper/2406.08223/) (2024)
- [Retrieval-Augmented Data Augmentation for Low-Resource Domain Tasks](https://mlsanity.com/paper/2402.13482/) (2024)
- [Towards Next-Generation Urban Decision Support Systems through AI-Powered Construction of Scientific Ontology using Large Language Models -- A Case in Optimizing Intermodal Freight Transportation](https://mlsanity.com/paper/2405.19255/) (2024)
- [Way to Specialist: Closing Loop Between Specialized LLM and Evolving Domain Knowledge Graph](https://mlsanity.com/paper/2411.19064/) (2024)
- [Aligning Knowledge Graphs and Language Models for Factual Accuracy](https://mlsanity.com/paper/2507.13411/) (2025)
- [Towards Ontology-Enhanced Representation Learning for Large Language Models](https://mlsanity.com/paper/2405.20527/) (2024)
- [Pretrained Generative Language Models as General Learning Frameworks for Sequence-Based Tasks](https://mlsanity.com/paper/2402.05616/) (2024)
- [Knowledge Pyramid Construction for Multi-Level Retrieval-Augmented Generation](https://mlsanity.com/paper/2407.21276/) (2024)
- [From PowerPoint UI Sketches to Web-Based Applications: Pattern-Driven Code Generation for GIS Dashboard Development Using Knowledge-Augmented LLMs, Context-Aware Visual Prompting, and the React Framework](https://mlsanity.com/paper/2502.08756/) (2025)
- [Knowledge Editing for Multi-Hop Question Answering Using Semantic Analysis](https://mlsanity.com/paper/2508.00914/) (2025)
- [Context-Aware Visual Prompting: Automating Geospatial Web Dashboards with Large Language Models and Agent Self-Validation for Decision Support](https://mlsanity.com/paper/2511.20656/) (2025)

## Abstract (arXiv)

Large Language Models (LLMs) exploit fine-tuning as a technique to adapt to diverse goals, thanks to task-specific training data. Task specificity should go hand in hand with domain orientation, that is, the specialization of an LLM to accurately address the tasks of a given realm of interest. However, models are usually fine-tuned over publicly available data or, at most, over ground data from databases, ignoring business-level definitions and domain experience. On the other hand, Enterprise Knowledge Graphs (EKGs) are able to capture and augment such domain knowledge via ontological reasoning. With the goal of combining LLM flexibility with the domain orientation of EKGs, we propose a novel neurosymbolic architecture that leverages the power of ontological reasoning to build task- and domain-specific corpora for LLM fine-tuning.