# Lies, Damned Lies, and Distributional Language Statistics: Persuasion and Deception with Large Language Models

arXiv: https://arxiv.org/abs/2412.17128 · HTML: https://mlsanity.com/paper/2412.17128/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Builds on 75 of its 266 references that are in the map.
- First posted on arXiv 22 Dec 2024.

## Builds on (most cited first, 30 of 75)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [Fine-Tuning Language Models from Human Preferences](https://mlsanity.com/paper/1909.08593/) (2019)
- [PaLM-E: An Embodied Multimodal Language Model](https://mlsanity.com/paper/2303.03378/) (2023)
- [Language Models (Mostly) Know What They Know](https://mlsanity.com/paper/2207.05221/) (2022)
- [WebGPT: Browser-assisted question-answering with human feedback](https://mlsanity.com/paper/2112.09332/) (2021)
- [Concrete Problems in AI Safety](https://mlsanity.com/paper/1606.06565/) (2016)
- [Representation Engineering: A Top-Down Approach to AI Transparency](https://mlsanity.com/paper/2310.01405/) (2023)
- [Inference-Time Intervention: Eliciting Truthful Answers from a Language Model](https://mlsanity.com/paper/2306.03341/) (2023)
- [The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery](https://mlsanity.com/paper/2408.06292/) (2024)
- [A General Language Assistant as a Laboratory for Alignment](https://mlsanity.com/paper/2112.00861/) (2021)
- [Language (Technology) is Power: A Critical Survey of "Bias" in NLP](https://mlsanity.com/paper/2005.14050/) (2020)
- [Show Your Work: Scratchpads for Intermediate Computation with Language Models](https://mlsanity.com/paper/2112.00114/) (2021)
- [Mechanistic Interpretability for AI Safety -- A Review](https://mlsanity.com/paper/2404.14082/) (2024)
- [AI safety via debate](https://mlsanity.com/paper/1805.00899/) (2018)
- [Quiet-STaR: Language Models Can Teach Themselves to Think Before Speaking](https://mlsanity.com/paper/2403.09629/) (2024)
- [AI Control: Improving Safety Despite Intentional Subversion](https://mlsanity.com/paper/2312.06942/) (2023)
- [Do the Rewards Justify the Means? Measuring Trade-Offs Between Rewards and Ethical Behavior in the MACHIAVELLI Benchmark](https://mlsanity.com/paper/2304.03279/) (2023)
- [FANToM: A Benchmark for Stress-testing Machine Theory of Mind in Interactions](https://mlsanity.com/paper/2310.15421/) (2023)
- [Alignment of Language Agents](https://mlsanity.com/paper/2103.14659/) (2021)
- [Monitoring AI-Modified Content at Scale: A Case Study on the Impact of ChatGPT on AI Conference Peer Reviews](https://mlsanity.com/paper/2403.07183/) (2024)
- [Generative Language Models and Automated Influence Operations: Emerging Threats and Potential Mitigations](https://mlsanity.com/paper/2301.04246/) (2023)
- [Large Language Models can Strategically Deceive their Users when Put Under Pressure](https://mlsanity.com/paper/2311.07590/) (2023)
- [Evaluating Frontier Models for Dangerous Capabilities](https://mlsanity.com/paper/2403.13793/) (2024)
- [Language Models Learn to Mislead Humans via RLHF](https://mlsanity.com/paper/2409.12822/) (2024)
- [Truthful AI: Developing and governing AI that does not lie](https://mlsanity.com/paper/2110.06674/) (2021)

## Built on by (most cited first, 15 of 15)

- [Large Language Models Pass the Turing Test](https://mlsanity.com/paper/2503.23674/) (2025)
- [Among Us: A Sandbox for Measuring and Detecting Agentic Deception](https://mlsanity.com/paper/2504.04072/) (2025)
- [The Levers of Political Persuasion with Conversational AI](https://mlsanity.com/paper/2507.13919/) (2025)
- [Thinking beyond the anthropomorphic paradigm benefits LLM research](https://mlsanity.com/paper/2502.09192/) (2025)
- [Do Large Language Models Have a Planning Theory of Mind? Evidence from MindGames: a Multi-Step Persuasion Task](https://mlsanity.com/paper/2507.16196/) (2025)
- [Commercial Persuasion in AI-Mediated Conversations](https://mlsanity.com/paper/2604.04263/) (2026)
- [Can (A)I Change Your Mind?](https://mlsanity.com/paper/2503.01844/) (2025)
- [AI-Enhanced Deliberative Democracy and the Future of the Collective Will](https://mlsanity.com/paper/2503.05830/) (2025)
- [Unraveling SITT: Social Influence Technique Taxonomy and Detection with LLMs](https://mlsanity.com/paper/2506.00061/) (2025)
- [PRISON: Unmasking the Criminal Potential of Large Language Models](https://mlsanity.com/paper/2506.16150/) (2025)
- [Large language models can effectively convince people to believe conspiracies](https://mlsanity.com/paper/2601.05050/) (2026)
- [How Open Must Language Models be to Enable Reliable Scientific Inference?](https://mlsanity.com/paper/2603.26539/) (2026)
- [Debate with Images: Detecting Deceptive Behaviors in Multimodal Large Language Models](https://mlsanity.com/paper/2512.00349/) (2025)
- [Large Language Models Persuade Without Planning Theory of Mind](https://mlsanity.com/paper/2602.17045/) (2026)
- [Learning with Conflicts of Interest](https://mlsanity.com/paper/2605.15504/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) can generate content that is as persuasive as human-written text and appear capable of selectively producing deceptive outputs. These capabilities raise concerns about potential misuse and unintended consequences as these systems become more widely deployed. This review synthesizes recent empirical work examining LLMs' capacity and proclivity for persuasion and deception, analyzes theoretical risks that could arise from these capabilities, and evaluates proposed mitigations. While current persuasive effects are relatively small, various mechanisms could increase their impact, including fine-tuning, multimodality, and social factors. We outline key open questions for future research, including how persuasive AI systems might become, whether truth enjoys an inherent advantage over falsehoods, and how effective different mitigation strategies may be in practice.