# The Anatomy of Speech Persuasion: Linguistic Shifts in LLM-Modified Speeches

arXiv: https://arxiv.org/abs/2506.18621 · HTML: https://mlsanity.com/paper/2506.18621/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 33 references that are in the map.
- First posted on arXiv 23 Jun 2025.

## Builds on (most cited first, 9 of 9)

- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [Does Writing with Language Models Reduce Content Diversity?](https://mlsanity.com/paper/2309.05196/) (2023)
- [Art or Artifice? Large Language Models and the False Promise of Creativity](https://mlsanity.com/paper/2309.14556/) (2023)
- [Winning Arguments: Interaction Dynamics and Persuasion Strategies in Good-faith Online Discussions](https://mlsanity.com/paper/1602.01103/) (2016)
- [The Curious Decline of Linguistic Diversity: Training Language Models on Synthetic Text](https://mlsanity.com/paper/2311.09807/) (2023)
- [Do Language Models Enjoy Their Own Stories? Prompting Large Language Models for Automatic Story Evaluation](https://mlsanity.com/paper/2405.13769/) (2024)
- [Automated assessment of non-native learner essays: Investigating the role of linguistic features](https://mlsanity.com/paper/1612.00729/) (2016)
- [LLM Cognitive Judgements Differ From Human](https://mlsanity.com/paper/2307.11787/) (2023)
- [STADEE: STAtistics-based DEEp Detection of Machine Generated Text](https://mlsanity.com/paper/2312.01672/) (2023)

## Abstract (arXiv)

This study examines how large language models understand the concept of persuasiveness in public speaking by modifying speech transcripts from PhD candidates in the "Ma These en 180 Secondes" competition, using the 3MT French dataset. Our contributions include a novel methodology and an interpretable textual feature set integrating rhetorical devices and discourse markers. We prompt GPT-4o to enhance or diminish persuasiveness and analyze linguistic shifts between original and generated speech in terms of the new features. Results indicate that GPT-4o applies systematic stylistic modifications rather than optimizing persuasiveness in a human-like manner. Notably, it manipulates emotional lexicon and syntactic structures (such as interrogative and exclamatory clauses) to amplify rhetorical impact.