Prove Your Point!: Bringing Proof-Enhancement Principles to Argumentative Essay Generation
This addresses the issue of logical confusion in argumentative essay generation for applications like automated writing assistance, though it is incremental as it builds on existing methods with a focus on proof principles.
The paper tackles the problem of generating argumentative essays with poor logical connections by introducing a two-stage framework (PESA) that enhances logical consistency, resulting in essays with better logical validity and persuasiveness compared to baseline models.
Argumentative essay generation (AEG) aims to generate complete texts on specific controversial topics or debates. Although current AEG methods can generate individual opinions, they often overlook the high-level connections between these opinions. This often leads to the generated results being mired in logical confusion, unable to proof their own arguments effectively. The generated essay may present evidence that contradicts the claims or they may fail to assemble the claims into logical flow. In this paper, we present a unified two-stage framework: Proof-Enhancement and Self-Annotation (PESA) for AEG with a focus on logical enhancement. Specifically, we first construct pseudo-labels for logical information,claims and grounds, using a large language model. We then propose a tree planning approach that introduces proof principles and ensures logical consistency. Extensive experimental results show that, benefiting from proof principle guidance, PESA generates argumentative essays with better logical validity and persuasiveness than strong baseline models.