# A Mechanism-Based Approach to Mitigating Harms from Persuasive Generative AI

arXiv: https://arxiv.org/abs/2404.15058 · HTML: https://mlsanity.com/paper/2404.15058/

## Key facts

- Cited by 34 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Apr 2024.

## Built on by (most cited first, 30 of 34)

- [LLMs achieve adult human performance on higher-order theory of mind tasks](https://mlsanity.com/paper/2405.18870/) (2024)
- [Large Language Models Pass the Turing Test](https://mlsanity.com/paper/2503.23674/) (2025)
- [Why human-AI relationships need socioaffective alignment](https://mlsanity.com/paper/2502.02528/) (2025)
- [Measuring and Benchmarking Large Language Models' Capabilities to Generate Persuasive Language](https://mlsanity.com/paper/2406.17753/) (2024)
- [Towards Trustworthy AI: A Review of Ethical and Robust Large Language Models](https://mlsanity.com/paper/2407.13934/) (2024)
- [Virtual Agent Economies](https://mlsanity.com/paper/2509.10147/) (2025)
- [The Levers of Political Persuasion with Conversational AI](https://mlsanity.com/paper/2507.13919/) (2025)
- [Epistemic Injustice in Generative AI](https://mlsanity.com/paper/2408.11441/) (2024)
- [Can LLMs make trade-offs involving stipulated pain and pleasure states?](https://mlsanity.com/paper/2411.02432/) (2024)
- [Lies, Damned Lies, and Distributional Language Statistics: Persuasion and Deception with Large Language Models](https://mlsanity.com/paper/2412.17128/) (2024)
- [Must Read: A Comprehensive Survey of Computational Persuasion](https://mlsanity.com/paper/2505.07775/) (2025)
- [Evidence of a log scaling law for political persuasion with large language models](https://mlsanity.com/paper/2406.14508/) (2024)
- [Towards Strategic Persuasion with Language Models](https://mlsanity.com/paper/2509.22989/) (2025)
- [Sociotechnical Implications of Generative Artificial Intelligence for Information Access](https://mlsanity.com/paper/2405.11612/) (2024)
- [Full-Stack Alignment: Co-Aligning AI and Institutions with Thick Models of Value](https://mlsanity.com/paper/2512.03399/) (2025)
- [Evaluating Language Models for Harmful Manipulation](https://mlsanity.com/paper/2603.25326/) (2026)
- [On the attribution of confidence to large language models](https://mlsanity.com/paper/2407.08388/) (2024)
- [How will advanced AI systems impact democracy?](https://mlsanity.com/paper/2409.06729/) (2024)
- [ChatbotManip: A Dataset to Facilitate Evaluation and Oversight of Manipulative Chatbot Behaviour](https://mlsanity.com/paper/2506.12090/) (2025)
- [Understanding Gender Bias in AI-Generated Product Descriptions](https://mlsanity.com/paper/2506.05390/) (2025)
- [Unraveling SITT: Social Influence Technique Taxonomy and Detection with LLMs](https://mlsanity.com/paper/2506.00061/) (2025)
- [Using Cognitive Models to Improve Language Model Simulation of Human Persuasion Games](https://mlsanity.com/paper/2606.17657/) (2026)
- [Can Large Language Models Predict Associations Among Human Attitudes?](https://mlsanity.com/paper/2503.21011/) (2025)
- [Beyond Accuracy: Rethinking Hallucination and Regulatory Response in Generative AI](https://mlsanity.com/paper/2509.13345/) (2025)
- [Large Language Models Persuade Without Planning Theory of Mind](https://mlsanity.com/paper/2602.17045/) (2026)
- [DeliberationBench: A Normative Benchmark for the Influence of Large Language Models on Users' Views](https://mlsanity.com/paper/2603.10018/) (2026)
- [Artificial intelligence can persuade people to take political actions](https://mlsanity.com/paper/2604.09200/) (2026)
- [Inducing language models to assert their own consciousness restores human beliefs and values](https://mlsanity.com/paper/2607.28607/) (2026)
- [Emergent Persuasion: Will LLMs Persuade Without Being Prompted?](https://mlsanity.com/paper/2512.22201/) (2025)
- [Information Access of the Oppressed: Freirean Design for Emancipatory Information Access](https://mlsanity.com/paper/2601.09600/) (2026)

## Abstract (arXiv)

Recent generative AI systems have demonstrated more advanced persuasive capabilities and are increasingly permeating areas of life where they can influence decision-making. Generative AI presents a new risk profile of persuasion due the opportunity for reciprocal exchange and prolonged interactions. This has led to growing concerns about harms from AI persuasion and how they can be mitigated, highlighting the need for a systematic study of AI persuasion. The current definitions of AI persuasion are unclear and related harms are insufficiently studied. Existing harm mitigation approaches prioritise harms from the outcome of persuasion over harms from the process of persuasion. In this paper, we lay the groundwork for the systematic study of AI persuasion. We first put forward definitions of persuasive generative AI. We distinguish between rationally persuasive generative AI, which relies on providing relevant facts, sound reasoning, or other forms of trustworthy evidence, and manipulative generative AI, which relies on taking advantage of cognitive biases and heuristics or misrepresenting information. We also put forward a map of harms from AI persuasion, including definitions and examples of economic, physical, environmental, psychological, sociocultural, political, privacy, and autonomy harm. We then introduce a map of mechanisms that contribute to harmful persuasion. Lastly, we provide an overview of approaches that can be used to mitigate against process harms of persuasion, including prompt engineering for manipulation classification and red teaming. Future work will operationalise these mitigations and study the interaction between different types of mechanisms of persuasion.