T-CPDL: A Temporal Causal Probabilistic Description Logic for Developing Logic-RAG Agent
This addresses the need for more robust, explainable, and trustworthy decision-making in language models, particularly for applications requiring temporal and causal reasoning, though it appears incremental as an extension of existing Description Logic frameworks.
The authors tackled the problem of large language models struggling with structured reasoning involving temporal constraints, causal relationships, and probabilistic reasoning by proposing Temporal Causal Probabilistic Description Logic (T-CPDL), which substantially improves inference accuracy, interpretability, and confidence calibration on temporal reasoning and causal inference benchmarks.
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.