T-CPDL: A Temporal Causal Probabilistic Description Logic for Developing Logic-RAG Agent

TL;DR

T-CPDL introduces an extended logic framework combining temporal, causal, and probabilistic reasoning to improve language models' interpretability, accuracy, and trustworthiness in complex reasoning tasks.

Contribution

It develops a novel integrated logic system with two variants for temporal and causal reasoning, enhancing language models' reasoning capabilities and explainability.

Findings

Significantly improves inference accuracy on reasoning benchmarks.

Enhances interpretability and confidence calibration of language model outputs.

Facilitates development of advanced Logic-RAG systems for knowledge-based reasoning.

Abstract

Large language models excel at generating fluent text but frequently struggle with structured reasoning involving temporal constraints, causal relationships, and probabilistic reasoning. To address these limitations, we propose Temporal Causal Probabilistic Description Logic (T-CPDL), an integrated framework that extends traditional Description Logic with temporal interval operators, explicit causal relationships, and probabilistic annotations. We present two distinct variants of T-CPDL: one capturing qualitative temporal relationships through Allen's interval algebra, and another variant enriched with explicit timestamped causal assertions. Both variants share a unified logical structure, enabling complex reasoning tasks ranging from simple temporal ordering to nuanced probabilistic causation. Empirical evaluations on temporal reasoning and causal inference benchmarks confirm that T-CPDL substantially improves inference accuracy, interpretability, and confidence calibration of language model outputs. By delivering transparent reasoning paths and fine-grained temporal and causal semantics, T-CPDL significantly enhances the capability of language models to support robust, explainable, and trustworthy decision-making. This work also lays the groundwork for developing advanced Logic-Retrieval-Augmented Generation (Logic-RAG) frameworks, potentially boosting the reasoning capabilities and efficiency of knowledge graph-enhanced RAG systems.