# A Model of Multi-turn Human Persuadability Using Probabilistic Belief Tracing

arXiv: https://arxiv.org/abs/2606.05330 · HTML: https://mlsanity.com/paper/2606.05330/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 61 of its 169 references that are in the map.
- First posted on arXiv 3 Jun 2026.

## Builds on (most cited first, 30 of 61)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Concrete Problems in AI Safety](https://mlsanity.com/paper/1606.06565/) (2016)
- [Towards Measuring the Representation of Subjective Global Opinions in Language Models](https://mlsanity.com/paper/2306.16388/) (2023)
- [AI safety via debate](https://mlsanity.com/paper/1805.00899/) (2018)
- [Debating with More Persuasive LLMs Leads to More Truthful Answers](https://mlsanity.com/paper/2402.06782/) (2024)
- [S3: Social-network Simulation System with Large Language Model-Empowered Agents](https://mlsanity.com/paper/2307.14984/) (2023)
- [AI Control: Improving Safety Despite Intentional Subversion](https://mlsanity.com/paper/2312.06942/) (2023)
- [AI Deception: A Survey of Examples, Risks, and Potential Solutions](https://mlsanity.com/paper/2308.14752/) (2023)
- [A Roadmap to Pluralistic Alignment](https://mlsanity.com/paper/2402.05070/) (2024)
- [Model evaluation for extreme risks](https://mlsanity.com/paper/2305.15324/) (2023)
- [Co-Writing with Opinionated Language Models Affects Users' Views](https://mlsanity.com/paper/2302.00560/) (2023)
- [Evaluating Frontier Models for Dangerous Capabilities](https://mlsanity.com/paper/2403.13793/) (2024)
- [From Word Models to World Models: Translating from Natural Language to the Probabilistic Language of Thought](https://mlsanity.com/paper/2306.12672/) (2023)
- [Winning Arguments: Interaction Dynamics and Persuasion Strategies in Good-faith Online Discussions](https://mlsanity.com/paper/1602.01103/) (2016)
- [On the Conversational Persuasiveness of Large Language Models: A Randomized Controlled Trial](https://mlsanity.com/paper/2403.14380/) (2024)
- [Are Large Language Models Consistent over Value-laden Questions?](https://mlsanity.com/paper/2407.02996/) (2024)
- [The Persuasive Power of Large Language Models](https://mlsanity.com/paper/2312.15523/) (2023)
- [Characterizing Manipulation from AI Systems](https://mlsanity.com/paper/2303.09387/) (2023)
- [Honesty Is the Best Policy: Defining and Mitigating AI Deception](https://mlsanity.com/paper/2312.01350/) (2023)
- [Beyond Demographics: Aligning Role-playing LLM-based Agents Using Human Belief Networks](https://mlsanity.com/paper/2406.17232/) (2024)
- [Argument Strength is in the Eye of the Beholder: Audience Effects in Persuasion](https://mlsanity.com/paper/1708.09085/) (2017)
- [A Mechanism-Based Approach to Mitigating Harms from Persuasive Generative AI](https://mlsanity.com/paper/2404.15058/) (2024)
- [Persuasion with Large Language Models: A Survey of Empirical Evidence, Study Methodologies, and Ethical Implications](https://mlsanity.com/paper/2411.06837/) (2024)
- [Exploring the Role of Prior Beliefs for Argument Persuasion](https://mlsanity.com/paper/1906.11301/) (2019)
- [Measuring and Benchmarking Large Language Models' Capabilities to Generate Persuasive Language](https://mlsanity.com/paper/2406.17753/) (2024)
- [Persuade Me if You Can: A Framework for Evaluating Persuasion Effectiveness and Susceptibility Among Large Language Models](https://mlsanity.com/paper/2503.01829/) (2025)
- [LLM Can be a Dangerous Persuader: Empirical Study of Persuasion Safety in Large Language Models](https://mlsanity.com/paper/2504.10430/) (2025)
- [Characterizing Delusional Spirals through Human-LLM Chat Logs](https://mlsanity.com/paper/2603.16567/) (2026)
- [Training LLMs for Honesty via Confessions](https://mlsanity.com/paper/2512.08093/) (2025)

## Abstract (arXiv)

Large language models can shift human beliefs across high-stakes domains, but most persuasion studies rely on pre/post belief change. These endpoint measures identify whether persuasion occurred, yet miss where and how beliefs moved within a dialogue. We present PERSUASIONTRACE, a framework for studying persuasion in human-LLM interaction. Built on a web-based experimental platform, PERSUASIONTRACE contributes a tool for multi-turn persuasion studies and a process-level evaluation protocol: it records multi-turn belief reports from human or simulated targets of persuasion, annotates persuader turns with rhetorical dimensions (logos/pathos/ethos), and evaluates simulators by fidelity to real human belief dynamics. Using this framework, we find that human targets group into two clusters of multi-turn belief updates and exhibit susceptibility to rhetorical strategies, and that LLMs are persuasive across generic and personalized topics, text and audio modalities, and multi-turn interactions. Prior work has chiefly used vanilla-prompted LLMs to simulate human targets, but we show that these simulators fail to replicate human belief dynamics. We introduce a Bayesian-network simulated target that maintains an explicit latent belief state over time so each persuader message yields cognitively realistic belief updates. In human-likeness evaluation, our Bayesian target scores near a human reference (81 vs 80), while baseline LLM targets score substantially lower (64). PERSUASIONTRACE reframes persuasion evaluation from endpoint movement alone to process fidelity, providing a stronger basis for scientific analysis and safer optimization of persuasive systems.