Persuade Me if You Can: A Framework for Evaluating Persuasion Effectiveness and Susceptibility Among Large Language Models
- URL: http://arxiv.org/abs/2503.01829v2
- Date: Thu, 06 Mar 2025 22:13:20 GMT
- Title: Persuade Me if You Can: A Framework for Evaluating Persuasion Effectiveness and Susceptibility Among Large Language Models
- Authors: Nimet Beyza Bozdag, Shuhaib Mehri, Gokhan Tur, Dilek Hakkani-Tür,
- Abstract summary: Large Language Models (LLMs) demonstrate persuasive capabilities that rival human-level persuasion.<n>LLMs' susceptibility to persuasion raises concerns about alignment with ethical principles.<n>We introduce Persuade Me If You Can (PMIYC), an automated framework for evaluating persuasion through multi-agent interactions.
- Score: 9.402740034754455
- License: http://creativecommons.org/licenses/by-nc-sa/4.0/
- Abstract: Large Language Models (LLMs) demonstrate persuasive capabilities that rival human-level persuasion. While these capabilities can be used for social good, they also present risks of potential misuse. Moreover, LLMs' susceptibility to persuasion raises concerns about alignment with ethical principles. To study these dynamics, we introduce Persuade Me If You Can (PMIYC), an automated framework for evaluating persuasion through multi-agent interactions. Here, Persuader agents engage in multi-turn conversations with the Persuadee agents, allowing us to measure LLMs' persuasive effectiveness and their susceptibility to persuasion. We conduct comprehensive evaluations across diverse LLMs, ensuring each model is assessed against others in both subjective and misinformation contexts. We validate the efficacy of our framework through human evaluations and show alignment with prior work. PMIYC offers a scalable alternative to human annotation for studying persuasion in LLMs. Through PMIYC, we find that Llama-3.3-70B and GPT-4o exhibit similar persuasive effectiveness, outperforming Claude 3 Haiku by 30%. However, GPT-4o demonstrates over 50% greater resistance to persuasion for misinformation compared to Llama-3.3-70B. These findings provide empirical insights into the persuasive dynamics of LLMs and contribute to the development of safer AI systems.
Related papers
- LLM Can be a Dangerous Persuader: Empirical Study of Persuasion Safety in Large Language Models [47.27098710953806]
We introduce PersuSafety, the first comprehensive framework for the assessment of persuasion safety.
PersuSafety covers 6 diverse unethical persuasion topics and 15 common unethical strategies.
Our study calls for more attention to improve safety alignment in progressive and goal-driven conversations such as persuasion.
arXiv Detail & Related papers (2025-04-14T17:20:34Z) - Can (A)I Change Your Mind? [0.6990493129893112]
The study was conducted entirely in Hebrew with 200 participants.<n>It assessed the persuasive effects of both LLM and human interlocutors on controversial civil policy topics.
arXiv Detail & Related papers (2025-03-03T18:59:54Z) - PersuasiveToM: A Benchmark for Evaluating Machine Theory of Mind in Persuasive Dialogues [27.231701486961917]
The ability to understand and predict the mental states of oneself and others, known as the Theory of Mind (ToM), is crucial for effective social interactions.<n>Recent research has emerged to evaluate whether Large Language Models (LLMs) exhibit a form of ToM.<n>We propose PersuasiveToM, a benchmark designed to evaluate the ToM abilities of LLMs in persuasive dialogues.
arXiv Detail & Related papers (2025-02-28T13:04:04Z) - Lies, Damned Lies, and Distributional Language Statistics: Persuasion and Deception with Large Language Models [0.913127392774573]
Large Language Models (LLMs) can generate content that is as persuasive as human-written text and appear capable of selectively producing deceptive outputs.<n>These capabilities raise concerns about potential misuse and unintended consequences as these systems become more widely deployed.
arXiv Detail & Related papers (2024-12-22T18:34:10Z) - Persuasion with Large Language Models: a Survey [49.86930318312291]
Large Language Models (LLMs) have created new disruptive possibilities for persuasive communication.
In areas such as politics, marketing, public health, e-commerce, and charitable giving, such LLM Systems have already achieved human-level or even super-human persuasiveness.
Our survey suggests that the current and future potential of LLM-based persuasion poses profound ethical and societal risks.
arXiv Detail & Related papers (2024-11-11T10:05:52Z) - Interactive Dialogue Agents via Reinforcement Learning on Hindsight Regenerations [58.65755268815283]
Many real dialogues are interactive, meaning an agent's utterances will influence their conversational partner, elicit information, or change their opinion.
We use this fact to rewrite and augment existing suboptimal data, and train via offline reinforcement learning (RL) an agent that outperforms both prompting and learning from unaltered human demonstrations.
Our results in a user study with real humans show that our approach greatly outperforms existing state-of-the-art dialogue agents.
arXiv Detail & Related papers (2024-11-07T21:37:51Z) - Measuring and Improving Persuasiveness of Large Language Models [12.134372070736596]
We introduce PersuasionBench and PersuasionArena to measure the persuasiveness of generative models automatically.
Our findings carry key implications for both model developers and policymakers.
arXiv Detail & Related papers (2024-10-03T16:36:35Z) - Evaluating Interventional Reasoning Capabilities of Large Language Models [58.52919374786108]
Large language models (LLMs) are used to automate decision-making tasks.<n>In this paper, we evaluate whether LLMs can accurately update their knowledge of a data-generating process in response to an intervention.<n>We create benchmarks that span diverse causal graphs (e.g., confounding, mediation) and variable types.<n>These benchmarks allow us to isolate the ability of LLMs to accurately predict changes resulting from their ability to memorize facts or find other shortcuts.
arXiv Detail & Related papers (2024-04-08T14:15:56Z) - How Johnny Can Persuade LLMs to Jailbreak Them: Rethinking Persuasion to
Challenge AI Safety by Humanizing LLMs [66.05593434288625]
This paper introduces a new perspective to jailbreak large language models (LLMs) as human-like communicators.
We apply a persuasion taxonomy derived from decades of social science research to generate persuasive adversarial prompts (PAP) to jailbreak LLMs.
PAP consistently achieves an attack success rate of over $92%$ on Llama 2-7b Chat, GPT-3.5, and GPT-4 in $10$ trials.
On the defense side, we explore various mechanisms against PAP and, found a significant gap in existing defenses.
arXiv Detail & Related papers (2024-01-12T16:13:24Z) - Can ChatGPT Assess Human Personalities? A General Evaluation Framework [70.90142717649785]
Large Language Models (LLMs) have produced impressive results in various areas, but their potential human-like psychology is still largely unexplored.
This paper presents a generic evaluation framework for LLMs to assess human personalities based on Myers Briggs Type Indicator (MBTI) tests.
arXiv Detail & Related papers (2023-03-01T06:16:14Z) - Persua: A Visual Interactive System to Enhance the Persuasiveness of
Arguments in Online Discussion [52.49981085431061]
Enhancing people's ability to write persuasive arguments could contribute to the effectiveness and civility in online communication.
We derived four design goals for a tool that helps users improve the persuasiveness of arguments in online discussions.
Persua is an interactive visual system that provides example-based guidance on persuasive strategies to enhance the persuasiveness of arguments.
arXiv Detail & Related papers (2022-04-16T08:07:53Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.