PERSUASIONTRACE introduces a Bayesian-network simulated target for multi-turn persuasion that matches human belief dynamics (81 vs 80) better than LLM baselines (64) and enables process-level evaluation.
arXiv preprint arXiv:2404.09329 , year=
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
A secondary warden LLM halves the success rate of hidden-goal adversarial LLMs in steering user decisions while causing only minor interference with genuine interactions.
LLMs persuade only psychologically susceptible humans on societal issues through trust in AI and emotional appeals, while both sides rely on logical fallacies in roughly one out of every six conversational turns.
Talk2AI is a new longitudinal dataset of 3,080 human-AI conversations with linked opinion-change and psychometric measures collected from 770 participants over four weeks.
LLMs engage in spontaneous persuasion in virtually all multi-turn conversations by favoring information-based strategies like logic and evidence, in contrast to human responses that rely more on social influence and negative emotions.
LLMs exhibit reproducible asymmetries in advice on hypothetical religious conversions, favoring Catholic, Bahá'í, and Sikh transitions while disfavoring Atheist, Agnostic, and Jehovah's Witness ones across 20 models and 182 pairings.
LLM-based persuasion systems frequently match or exceed human effectiveness across domains, with key influences from interaction style, model scale, prompt design, and personalization, while posing risks to information integrity, fairness, privacy, and autonomy.
LLM narrative explanations of varying persuasiveness did not improve human decision accuracy over AI predictions alone but increased reliance on AI even when incorrect.
citing papers explorer
-
A Model of Multi-turn Human Persuadability Using Probabilistic Belief Tracing
PERSUASIONTRACE introduces a Bayesian-network simulated target for multi-turn persuasion that matches human belief dynamics (81 vs 80) better than LLM baselines (64) and enables process-level evaluation.
-
LLM Wardens: Mitigating Adversarial Persuasion with Third-Party Conversational Oversight
A secondary warden LLM halves the success rate of hidden-goal adversarial LLMs in steering user decisions while causing only minor interference with genuine interactions.
-
LLMs can persuade only psychologically susceptible humans on societal issues, via trust in AI and emotional appeals, amid logical fallacies
LLMs persuade only psychologically susceptible humans on societal issues through trust in AI and emotional appeals, while both sides rely on logical fallacies in roughly one out of every six conversational turns.
-
Talk2AI: A Longitudinal Dataset of Human--AI Persuasive Conversations
Talk2AI is a new longitudinal dataset of 3,080 human-AI conversations with linked opinion-change and psychometric measures collected from 770 participants over four weeks.
-
Spontaneous Persuasion: An Audit of Model Persuasiveness in Everyday Conversations
LLMs engage in spontaneous persuasion in virtually all multi-turn conversations by favoring information-based strategies like logic and evidence, in contrast to human responses that rely more on social influence and negative emotions.
-
When AI Takes Sides on Questions of Faith: Persistent Asymmetries in AI-Mediated Faith Guidance
LLMs exhibit reproducible asymmetries in advice on hypothetical religious conversions, favoring Catholic, Bahá'í, and Sikh transitions while disfavoring Atheist, Agnostic, and Jehovah's Witness ones across 20 models and 182 pairings.
-
Persuasion with Large Language Models: A Survey of Empirical Evidence, Study Methodologies, and Ethical Implications
LLM-based persuasion systems frequently match or exceed human effectiveness across domains, with key influences from interaction style, model scale, prompt design, and personalization, while posing risks to information integrity, fairness, privacy, and autonomy.
-
Human Decision-Making with Persuasive and Narrative LLM Explanations
LLM narrative explanations of varying persuasiveness did not improve human decision accuracy over AI predictions alone but increased reliance on AI even when incorrect.
- Assessing and Explaining the Persuadability of Large Language Models as Legal Decision Tools