Prove Your Point!: Bringing Proof-Enhancement Principles to Argumentative Essay Generation
Ruiyu Xiao, Lei Wu, Yuhang Gou, Weinan Zhang, Ting Liu

TL;DR
This paper introduces PESA, a two-stage framework for argumentative essay generation that enhances logical consistency and persuasiveness by incorporating proof principles and self-annotation, leading to more coherent and convincing essays.
Contribution
The paper proposes a novel two-stage framework, PESA, which integrates proof principles and pseudo-labeling to improve logical coherence in automated argumentative essay generation.
Findings
PESA outperforms baseline models in logical validity.
Enhanced logical consistency improves persuasiveness.
Tree planning ensures coherent argument structure.
Abstract
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…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
Taxonomy
TopicsModel-Driven Software Engineering Techniques · Software Engineering Research · Writing and Handwriting Education
MethodsFocus
