ENTRUST: Argument Reframing with Language Models and Entailment
This addresses the challenge of influencing opinions and beliefs through lexical framing, with incremental improvements in a domain-specific task.
The paper tackled the problem of reframing arguments to have positive effects by creating a dataset and a method that combines controllable text generation with an entailment component, showing effectiveness in fluency, meaning, and trustworthiness compared to strong baselines.
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.