A New Framework for Formal Reasoning over Symbolic and Sub-Symbolic Knowledge

A Primer on Computational Semantics for Artificial Intelligence Systems

As people adopt transformer-based language models (e.g., ChatGPT and Gemini) for an increasing number of use-cases, it is important to know how such models learn and represent the meaning of the language, and to be more informed about what language is. This document is an attempt to help the reader understand how lingu...

A General Form of Cautious Approximate Reasoning for Symbolic and Complex Data

Abstract Decision-makers are increasingly confronted with the problem of data imprecision. Thereby,the representation and manipulation of such knowledge play a crucial role in the performance of intelligent systems. Among the well-known logics for imprecise data, we can find symbolic multi-valued logic. This logic exte...

Co-Evolving Structured Knowledge and Reasoning in Language Models

Kevo is a co-evolving framework that jointly learns to construct a structured knowledge base and reason over it for knowledge-intensive question answering, which leads to larger, better-connected knowledge structures with higher answer reachability, while also improving compositional factual reasoning and controllabili...

Syntactic Simplification of OWL Class Expressions

This paper proposes Class Expression Simplifier (CES), a novel algorithm for the syntactic simplification of class expressions in Description Logics (DL), which aims to preserve formal semantics while reducing representational complexity.

Taxonomy Exploration with Large Language Model Reasoning and Tool Calling

Toward Effective and Reliable LLM Agents via Dynamic Ontology

OaK is presented, an ontology-as-a-kernel framework that dynamically constructs and refines task-oriented ontologies for LLM agents and shows that OaK improves standard LLM agents, strengthens evidence grounding, and boosts the reliability of multi-step reasoning.