ProSLM : A Prolog Synergized Language Model for explainable Domain Specific Knowledge Based Question Answering

TL;DR

ProSLM integrates formal logic with large language models to enhance explainability, accuracy, and robustness in domain-specific question answering by providing context generation and validation against a knowledge base.

Contribution

The paper introduces ProSLM, a neurosymbolic framework combining logic and LLMs for explainable, reliable domain-specific question answering with context and validation capabilities.

Findings

Improves factual accuracy in LLM-based QA

Provides explainable context generation

Enhances robustness through logical validation

Abstract

Neurosymbolic approaches can add robustness to opaque neural systems by incorporating explainable symbolic representations. However, previous approaches have not used formal logic to contextualize queries to and validate outputs of large language models (LLMs). We propose \systemname{}, a novel neurosymbolic framework, to improve the robustness and reliability of LLMs in question-answering tasks. We provide \systemname{} with a domain-specific knowledge base, a logical reasoning system, and an integration to an existing LLM. This framework has two capabilities (1) context gathering: generating explainable and relevant context for a given query, and (2) validation: confirming and validating the factual accuracy of a statement in accordance with a knowledge base (KB). Our work opens a new area of neurosymbolic generative AI text validation and user personalization.