# Bounded Fitting for Expressive Description Logics

arXiv: https://arxiv.org/abs/2605.07452 · HTML: https://mlsanity.com/paper/2605.07452/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 35 references that are in the map.
- First posted on arXiv 8 May 2026.

## Builds on (most cited first, 7 of 7)

- [Learning Linear Temporal Properties](https://mlsanity.com/paper/1806.03953/) (2018)
- [YAGO 4.5: A Large and Clean Knowledge Base with a Rich Taxonomy](https://mlsanity.com/paper/2308.11884/) (2023)
- [EvoLearner: Learning Description Logics with Evolutionary Algorithms](https://mlsanity.com/paper/2111.04879/) (2021)
- [Logical Separability of Labeled Data Examples under Ontologies](https://mlsanity.com/paper/2007.01610/) (2020)
- [SAT-Based PAC Learning of Description Logic Concepts](https://mlsanity.com/paper/2305.08511/) (2023)
- [SAT-based Learning of Computation Tree Logic](https://mlsanity.com/paper/2402.06366/) (2024)
- [SAT-Based Bounded Fitting for the Description Logic ALC](https://mlsanity.com/paper/2507.21752/) (2025)

## Abstract (arXiv)

Bounded fitting is an attractive paradigm for learning logical formulas from labeled data examples that offers PAC-style generalization guarantees and can often be implemented leveraging SAT solvers. It has been successfully applied to learning concepts of the description logic ALC. We study bounded fitting for learning concepts in expressive description logics that extend ALC with inverse roles, qualified number restrictions, and feature comparisons. We investigate under which conditions bounded fitting keeps its favorable theoretical properties in this setting, and implement it using a SAT solver. We compare our tool with state-of-the-art concept learners with encouraging results, demonstrating that it is a practical approach to expressive concept learning.