ENTRUST: Argument Reframing with Language Models and Entailment

TL;DR

This paper introduces ENTRUST, a method that uses language models and entailment to reframe arguments with positive connotations, aiming to influence opinions while maintaining original meaning.

Contribution

It presents a novel dataset and a combined approach of controllable generation and entailment for lexical argument reframing.

Findings

Effective in improving fluency, meaning, and trustworthiness.

Outperforms strong baselines in argument reframing tasks.

Demonstrates potential for positive influence in argument presentation.

Abstract

Framing involves the positive or negative presentation of an argument or issue depending on the audience and goal of the speaker (Entman 1983). Differences in lexical framing, the focus of our work, can have large effects on peoples' opinions and beliefs. To make progress towards reframing arguments for positive effects, we create a dataset and method for this task. We use a lexical resource for "connotations" to create a parallel corpus and propose a method for argument reframing that combines controllable text generation (positive connotation) with a post-decoding entailment component (same denotation). Our results show that our method is effective compared to strong baselines along the dimensions of fluency, meaning, and trustworthiness/reduction of fear.