Prove Your Point!: Bringing Proof-Enhancement Principles to Argumentative Essay Generation
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 11 of its 24 references that are in the map. First posted on arXiv 30 Oct 2024.
Builds on
11 of 24 references.
References · 11
- 2023G-Eval: NLG Evaluation using GPT-4 with Better Human Alignmentcited by 2,205
- 2021Recursively Summarizing Books with Human Feedbackcited by 287
- 2020Evaluation of Text Generation: A Surveycited by 275
- 2017Learning Discourse-level Diversity for Neural Dialog Models using Conditional Variational Autoencoderscited by 222
- 2022Co-Writing Screenplays and Theatre Scripts with Language Models: An Evaluation by Industry Professionalscited by 191
- 2019Discourse-Aware Neural Extractive Text Summarizationcited by 104
- 2020Aspect-Controlled Neural Argument Generationcited by 43
- 2022PLANET: Dynamic Content Planning in Autoregressive Transformers for Long-form Text Generationcited by 30
- 2020The workweek is the best time to start a family -- A Study of GPT-2 Based Claim Generationcited by 15
- 2021DYPLOC: Dynamic Planning of Content Using Mixed Language Models for Text Generationcited by 11
- 2022Generating Coherent Narratives by Learning Dynamic and Discrete Entity States with a Contrastive Frameworkcited by 6
Built on by
Citing papers per year: 2026: 1.
1 paper.