# How Do LLMs Persuade? Linear Probes Can Uncover Persuasion Dynamics in Multi-Turn Conversations

arXiv: https://arxiv.org/abs/2508.05625 · HTML: https://mlsanity.com/paper/2508.05625/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Probing deception, bias and beliefs, one of 13 directions in Mechanistic interpretability.
- Builds on 21 of its 76 references that are in the map.
- First posted on arXiv 7 Aug 2025.

## Placed in

- Mechanistic interpretability / [Probing deception, bias and beliefs](https://mlsanity.com/mechinterp/probing-deception-bias-and-beliefs/)

## Builds on (most cited first, 21 of 21)

- [Understanding intermediate layers using linear classifier probes](https://mlsanity.com/paper/1610.01644/) (2016)
- [Steering Llama 2 via Contrastive Activation Addition](https://mlsanity.com/paper/2312.06681/) (2023)
- [Steering Language Models With Activation Engineering](https://mlsanity.com/paper/2308.10248/) (2023)
- [The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets](https://mlsanity.com/paper/2310.06824/) (2023)
- [How Johnny Can Persuade LLMs to Jailbreak Them: Rethinking Persuasion to Challenge AI Safety by Humanizing LLMs](https://mlsanity.com/paper/2401.06373/) (2024)
- [Cognitive Behaviors that Enable Self-Improving Reasoners, or, Four Habits of Highly Effective STaRs](https://mlsanity.com/paper/2503.01307/) (2025)
- [How NOT To Evaluate Your Dialogue System: An Empirical Study of Unsupervised Evaluation Metrics for Dialogue Response Generation](https://mlsanity.com/paper/1603.08023/) (2016)
- [Scalable and Transferable Black-Box Jailbreaks for Language Models via Persona Modulation](https://mlsanity.com/paper/2311.03348/) (2023)
- [Persuasion for Good: Towards a Personalized Persuasive Dialogue System for Social Good](https://mlsanity.com/paper/1906.06725/) (2019)
- [Large Language Models can Strategically Deceive their Users when Put Under Pressure](https://mlsanity.com/paper/2311.07590/) (2023)
- [Thinking Fast and Slow in Large Language Models](https://mlsanity.com/paper/2212.05206/) (2022)
- [Cognitive Overload: Jailbreaking Large Language Models with Overloaded Logical Thinking](https://mlsanity.com/paper/2311.09827/) (2023)
- [Detecting Strategic Deception Using Linear Probes](https://mlsanity.com/paper/2502.03407/) (2025)
- [CogBench: a large language model walks into a psychology lab](https://mlsanity.com/paper/2402.18225/) (2024)
- [Detecting High-Stakes Interactions with Activation Probes](https://mlsanity.com/paper/2506.10805/) (2025)
- [Measuring and Benchmarking Large Language Models' Capabilities to Generate Persuasive Language](https://mlsanity.com/paper/2406.17753/) (2024)
- [Large Language Models are as persuasive as humans, but how? About the cognitive effort and moral-emotional language of LLM arguments](https://mlsanity.com/paper/2404.09329/) (2024)
- [Foot In The Door: Understanding Large Language Model Jailbreaking via Cognitive Psychology](https://mlsanity.com/paper/2402.15690/) (2024)
- [Quality Does Matter: A Detailed Look at the Quality and Utility of Web-Mined Parallel Corpora](https://mlsanity.com/paper/2402.07446/) (2024)
- [A review on the use of large language models as virtual tutors](https://mlsanity.com/paper/2405.11983/) (2024)
- [Communication is All You Need: Persuasion Dataset Construction via Multi-LLM Communication](https://mlsanity.com/paper/2502.08896/) (2025)

## Built on by (most cited first, 4 of 4)

- [Sycophancy Is Not One Thing: Causal Separation of Sycophantic Behaviors in LLMs](https://mlsanity.com/paper/2509.21305/) (2025)
- [Accumulating Context Changes the Beliefs of Language Models](https://mlsanity.com/paper/2511.01805/) (2025)
- [The Hidden Puppet Master: Predicting Human Belief Change in Manipulative LLM Dialogues](https://mlsanity.com/paper/2603.20907/) (2026)
- [The AI's Poker Face: Contrasting Persuasion and Sycophancy in Voice-Based Multi-Turn Conversations](https://mlsanity.com/paper/2610.14124/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) have started to demonstrate the ability to persuade humans, yet our understanding of how this dynamic transpires is limited. Recent work has used linear probes, lightweight tools for analyzing model representations, to study various LLM skills such as the ability to model user sentiment and political perspective. Motivated by this, we apply probes to study persuasion dynamics in natural, multi-turn conversations. We leverage insights from cognitive science to train probes on distinct aspects of persuasion: persuasion success, persuadee personality, and persuasion strategy. Despite their simplicity, we show that they capture various aspects of persuasion at both the sample and dataset levels. For instance, probes can identify the point in a conversation where the persuadee was persuaded or where persuasive success generally occurs across the entire dataset. We also show that in addition to being faster than expensive prompting-based approaches, probes can do just as well and even outperform prompting in some settings, such as when uncovering persuasion strategy. This suggests probes as a plausible avenue for studying other complex behaviours such as deception and manipulation, especially in multi-turn settings and large-scale dataset analysis where prompting-based methods would be computationally inefficient.