# Tailored Truths: Optimizing LLM Persuasion with Personalization and Fabricated Statistics

arXiv: https://arxiv.org/abs/2501.17273 · HTML: https://mlsanity.com/paper/2501.17273/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 45 references that are in the map.
- First posted on arXiv 28 Jan 2025.

## Builds on (most cited first, 10 of 10)

- [Show Your Work: Scratchpads for Intermediate Computation with Language Models](https://mlsanity.com/paper/2112.00114/) (2021)
- [Mixture-of-Agents Enhances Large Language Model Capabilities](https://mlsanity.com/paper/2406.04692/) (2024)
- [Generative Language Models and Automated Influence Operations: Emerging Threats and Potential Mitigations](https://mlsanity.com/paper/2301.04246/) (2023)
- [On the Conversational Persuasiveness of Large Language Models: A Randomized Controlled Trial](https://mlsanity.com/paper/2403.14380/) (2024)
- [Can ChatGPT Defend its Belief in Truth? Evaluating LLM Reasoning via Debate](https://mlsanity.com/paper/2305.13160/) (2023)
- [The Persuasive Power of Large Language Models](https://mlsanity.com/paper/2312.15523/) (2023)
- [The language of opinion change on social media under the lens of communicative action](https://mlsanity.com/paper/2210.17234/) (2022)
- [The Dark Patterns of Personalized Persuasion in Large Language Models: Exposing Persuasive Linguistic Features for Big Five Personality Traits in LLMs Responses](https://mlsanity.com/paper/2411.06008/) (2024)
- [Studying User Footprints in Different Online Social Networks](https://mlsanity.com/paper/1301.6870/) (2013)
- [ConspEmoLLM: Conspiracy Theory Detection Using an Emotion-Based Large Language Model](https://mlsanity.com/paper/2403.06765/) (2024)

## Built on by (most cited first, 8 of 8)

- [It's the Thought that Counts: Evaluating the Attempts of Frontier LLMs to Persuade on Harmful Topics](https://mlsanity.com/paper/2506.02873/) (2025)
- [Belief-Sim: Towards Belief-Driven Simulation of Demographic Misinformation Susceptibility](https://mlsanity.com/paper/2603.03585/) (2026)
- ["I followed what felt right, not what I was told": Autonomy, Coaching, and Recognizing Bias Through AI-Mediated Dialogue](https://mlsanity.com/paper/2603.11274/) (2026)
- [To Lie or Not to Lie? Investigating The Biased Spread of Global Lies by LLMs](https://mlsanity.com/paper/2604.06552/) (2026)
- [Spontaneous Persuasion: An Audit of Model Persuasiveness in Everyday Conversations](https://mlsanity.com/paper/2604.22109/) (2026)
- [A Model of Multi-turn Human Persuadability Using Probabilistic Belief Tracing](https://mlsanity.com/paper/2606.05330/) (2026)
- [Belief Cascades Drive Persuasion in LLM Agent Networks](https://mlsanity.com/paper/2608.25152/) (2026)
- [CC-Mediation: Evaluating Large Language Models for Cross-Cultural Conflict Mediation](https://mlsanity.com/paper/2609.04855/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) are becoming increasingly persuasive, demonstrating the ability to personalize arguments in conversation with humans by leveraging their personal data. This may have serious impacts on the scale and effectiveness of disinformation campaigns. We studied the persuasiveness of LLMs in a debate setting by having humans (n=33) engage with LLM-generated arguments intended to change the human's opinion. We quantified the LLM's effect by measuring human agreement with the debate's hypothesis pre- and post-debate and analyzing both the magnitude of opinion change, as well as the likelihood of an update in the LLM's direction. We compare persuasiveness across established persuasion strategies, including personalized arguments informed by user demographics and personality, appeal to fabricated statistics, and a mixed strategy utilizing both personalized arguments and fabricated statistics. We found that static arguments generated by humans and GPT-4o-mini have comparable persuasive power. However, the LLM outperformed static human-written arguments when leveraging the mixed strategy in an interactive debate setting. This approach had a 51% chance of persuading participants to modify their initial position, compared to 32% for the static human-written arguments. Our results highlight the concerning potential for LLMs to enable inexpensive and persuasive large-scale disinformation campaigns.