Graph-Guided Textual Explanation Generation Framework

TL;DR

G-Tex is a novel framework that improves the faithfulness of natural language explanations by guiding their generation with graph-encoded highlight explanations reflecting the model's reasoning process.

Contribution

The paper introduces G-Tex, a graph-guided framework that enhances explanation faithfulness by integrating highlight explanations into NLE generation.

Findings

G-Tex improves NLE faithfulness by up to 12.18%.

G-Tex generates explanations closer to human-written ones.

Human evaluations show better quality and reduced redundancy.

Abstract

Natural language explanations (NLEs) are commonly used to provide plausible free-text explanations of a model's reasoning about its predictions. However, recent work has questioned their faithfulness, as they may not accurately reflect the model's internal reasoning process regarding its predicted answer. In contrast, highlight explanations--input fragments critical for the model's predicted answers--exhibit measurable faithfulness. Building on this foundation, we propose G-Tex, a Graph-Guided Textual Explanation Generation framework designed to enhance the faithfulness of NLEs. Specifically, highlight explanations are first extracted as faithful cues reflecting the model's reasoning logic toward answer prediction. They are subsequently encoded through a graph neural network layer to guide the NLE generation, which aligns the generated explanations with the model's underlying reasoning toward the predicted answer. Experiments on T5 and BART using three reasoning datasets show that G-Tex improves NLE faithfulness by up to 12.18% compared to baseline methods. Additionally, G-Tex generates NLEs with greater semantic and lexical similarity to human-written ones. Human evaluations show that G-Tex can decrease redundant content and enhance the overall quality of NLEs. Our work presents a novel method for explicitly guiding NLE generation to enhance faithfulness, serving as a foundation for addressing broader criteria in NLE and generated text.