Verification and Refinement of Natural Language Explanations through LLM-Symbolic Theorem Proving
This addresses the problem of logical errors in explanation evaluation for NLI researchers, though it is incremental as it builds on existing neuro-symbolic methods.
The paper tackles the challenge of verifying and refining natural language explanations for Natural Language Inference by integrating Large Language Models with Theorem Provers, resulting in a neuro-symbolic framework that provides formal guarantees and enhances explanation quality across domains.
Natural language explanations represent a proxy for evaluating explanation-based and multi-step Natural Language Inference (NLI) models. However, assessing the validity of explanations for NLI is challenging as it typically involves the crowd-sourcing of apposite datasets, a process that is time-consuming and prone to logical errors. To address existing limitations, this paper investigates the verification and refinement of natural language explanations through the integration of Large Language Models (LLMs) and Theorem Provers (TPs). Specifically, we present a neuro-symbolic framework, named Explanation-Refiner, that integrates TPs with LLMs to generate and formalise explanatory sentences and suggest potential inference strategies for NLI. In turn, the TP is employed to provide formal guarantees on the logical validity of the explanations and to generate feedback for subsequent improvements. We demonstrate how Explanation-Refiner can be jointly used to evaluate explanatory reasoning, autoformalisation, and error correction mechanisms of state-of-the-art LLMs as well as to automatically enhance the quality of explanations of variable complexity in different domains.