# A Generalizable Rhetorical Strategy Annotation Model Using LLM-based Debate Simulation and Labelling

arXiv: https://arxiv.org/abs/2510.15081 · HTML: https://mlsanity.com/paper/2510.15081/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 75 references that are in the map.
- First posted on arXiv 16 Oct 2025.

## Builds on (most cited first, 19 of 19)

- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Out of One, Many: Using Language Models to Simulate Human Samples](https://mlsanity.com/paper/2209.06899/) (2022)
- [Using Large Language Models to Simulate Multiple Humans and Replicate Human Subject Studies](https://mlsanity.com/paper/2208.10264/) (2022)
- [Adapted Large Language Models Can Outperform Medical Experts in Clinical Text Summarization](https://mlsanity.com/paper/2309.07430/) (2023)
- [Persuasion for Good: Towards a Personalized Persuasive Dialogue System for Social Good](https://mlsanity.com/paper/1906.06725/) (2019)
- [Two Tales of Persona in LLMs: A Survey of Role-Playing and Personalization](https://mlsanity.com/paper/2406.01171/) (2024)
- [Winning Arguments: Interaction Dynamics and Persuasion Strategies in Good-faith Online Discussions](https://mlsanity.com/paper/1602.01103/) (2016)
- [Is GPT-3 Text Indistinguishable from Human Text? Scarecrow: A Framework for Scrutinizing Machine Text](https://mlsanity.com/paper/2107.01294/) (2021)
- [A Large-scale Dataset for Argument Quality Ranking: Construction and Analysis](https://mlsanity.com/paper/1911.11408/) (2019)
- [Contrasting Linguistic Patterns in Human and LLM-Generated News Text](https://mlsanity.com/paper/2308.09067/) (2023)
- [Automatic Argument Quality Assessment -- New Datasets and Methods](https://mlsanity.com/paper/1909.01007/) (2019)
- [Finding Convincing Arguments Using Scalable Bayesian Preference Learning](https://mlsanity.com/paper/1806.02418/) (2018)
- [Weakly-Supervised Hierarchical Models for Predicting Persuasive Strategies in Good-faith Textual Requests](https://mlsanity.com/paper/2101.06351/) (2021)
- [Persuasive Natural Language Generation -- A Literature Review](https://mlsanity.com/paper/2101.05786/) (2021)
- [An Unsupervised Domain-Independent Framework for Automated Detection of Persuasion Tactics in Text](https://mlsanity.com/paper/1912.06745/) (2019)
- [Generating Educational Materials with Different Levels of Readability using LLMs](https://mlsanity.com/paper/2406.12787/) (2024)
- [Examining the Ordering of Rhetorical Strategies in Persuasive Requests](https://mlsanity.com/paper/2010.04625/) (2020)
- [Communication is All You Need: Persuasion Dataset Construction via Multi-LLM Communication](https://mlsanity.com/paper/2502.08896/) (2025)
- [PatternGPT :A Pattern-Driven Framework for Large Language Model Text Generation](https://mlsanity.com/paper/2307.00470/) (2023)

## Built on by (most cited first, 1 of 1)

- [Rhetorical Questions in LLM Representations: A Linear Probing Study](https://mlsanity.com/paper/2604.14128/) (2026)

## Abstract (arXiv)

Rhetorical strategies are central to persuasive communication, from political discourse and marketing to legal argumentation. However, analysis of rhetorical strategies has been limited by reliance on human annotation, which is costly, inconsistent, difficult to scale. Their associated datasets are often limited to specific topics and strategies, posing challenges for robust model development. We propose a novel framework that leverages large language models (LLMs) to automatically generate and label synthetic debate data based on a four-part rhetorical typology (causal, empirical, emotional, moral). We fine-tune transformer-based classifiers on this LLM-labeled dataset and validate its performance against human-labeled data on this dataset and on multiple external corpora. Our model achieves high performance and strong generalization across topical domains. We illustrate two applications with the fine-tuned model: (1) the improvement in persuasiveness prediction from incorporating rhetorical strategy labels, and (2) analyzing temporal and partisan shifts in rhetorical strategies in U.S. Presidential debates (1960-2020), revealing increased use of affective over cognitive argument in U.S. Presidential debates.