Skip to content

Modeling Bias in Machine Learning with Description Logics and Epistemic Modalities

2026 · Digital library · 0 citations · 8 references
Computer Science

TL;DR

This work develops a Description Logic–based general formalization of the structure underlying several types of bias, with explicit attention to the epistemic states of agents, to integrate ontological constraints with representations of agents’ epistemic attitudes, thereby connecting DL-based knowledge representation with epistemic reasoning.

View source

Similar papers

Sep 2026

Reasoning about the past in epistemic logic with separation

It is shown that, if the horizon of epistemic actions is bounded, the multiplicative connectives can be eliminated from a logical language with also epistemic and action model modalities.

H. van Ditmarsch, D. Galmiche · 0 citations
Review Open access Sep 2026

Enduring Strengths of Knowledge-Based Methods in the Era of Machine Learning and Large Language Models: A Task-and-Architecture Perspective

Large language models have shifted AI toward statistical learning, but knowledge-based methods remain essential for tasks governed by combinatorial structure, declarative correctness, strong domain priors, and auditable reasoning. This paper treats the issue as one of task–architecture fit rather than paradigm competit...

Maikel Leon · 0 citations
#natural language process... Preprint Sep 2026

From Token Probabilities to Semantic Constraints: Towards Declarative Probabilistic Evaluation of Language Models

A declarative probabilistic framework for pre-training evaluation that makes the semantic structure of model behavior explicit and provides new formal tools for relating evaluation to learning, and links evaluation and learning through a shared semantics.

Kyle Richardson, C. Anderson, Pranav Balakrishnan et al. · 1 citation
Open access Aug 2026

Knowledge and Information in Epistemic Dynamics

A general axiomatic definition of a cognitive system, along with its corresponding epistemic information measure, and it is demonstrated that Shannon’s source information, artificial neural networks, and formal logical theories are all concrete realizations of this unified framework.

Vincenzo Manca · 0 citations
#artificial intelligence Preprint Sep 2026

Semantic Bayesian World Models

Semantic Bayesian World Models are envisioned: a Web that describes the world not as a database of facts but as a shared, evolving fabric of beliefs over knowledge graphs, where ontological axioms constrain priors, observations update beliefs by Bayesian conditioning, and actions intervene upon the world.

Tommaso Soru · 0 citations
Conference Open access Sep 2026

Splitting Meanings: A Unified View on Paraconsistency and Inconsistency Measurement

A modular logical framework for both reasoning with and measuring inconsistency in propositional knowledge bases that captures several existing forms of inconsistency-tolerant reasoning, including entailment based on maximal satisfiable subsets and the minimally inconsistent Logic of Paradox.

Yakoub Salhi · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.