Making Implicit Premises Explicit in Logical Understanding of Enthymemes

TL;DR

This paper introduces a pipeline combining large language models and a neuro-symbolic reasoner to explicitly identify and decode implicit premises in enthymemes, enhancing logical understanding in NLP.

Contribution

It presents a systematic method for translating textual enthymemes into logical formulas and decoding their underlying logic using a hybrid approach.

Findings

Effective implicit premise selection with high precision and recall

Successful translation of natural language enthymemes into logical formulas

Promising results in logical entailment detection

Abstract

Real-world arguments in text and dialogues are normally enthymemes (i.e. some of their premises and/or claims are implicit). Natural language processing (NLP) methods for handling enthymemes can potentially identify enthymemes in text but they do not decode their underlying logic, whereas logic-based approaches for handling them assume a knowledgebase with sufficient formulae that can be used to decode them via abduction. There is therefore a lack of a systematic method for translating textual components of an enthymeme into a logical argument and generating the logical formulae required for their decoding, and thereby showing logical entailment. To address this, we propose a pipeline that integrates: (1) a large language model (LLM) to generate intermediate implicit premises based on the explicit premise and claim; (2) another LLM to translate the natural language into logical formulas; and (3) a neuro-symbolic reasoner based on a SAT solver to determine entailment. We evaluate our pipeline on two enthymeme datasets, demonstrating promising performance in selecting the correct implicit premise, as measured by precision, recall, F1-score, and accuracy.