I Want to Break Free! Persuasion and Anti-Social Behavior of LLMs in Multi-Agent Settings with Social Hierarchy

• URL: http://arxiv.org/abs/2410.07109v2
• Date: Wed, 16 Oct 2024 08:06:22 GMT
• Title: I Want to Break Free! Persuasion and Anti-Social Behavior of LLMs in Multi-Agent Settings with Social Hierarchy
• Authors: Gian Maria Campedelli, Nicolò Penzo, Massimo Stefan, Roberto Dessì, Marco Guerini, Bruno Lepri, Jacopo Staiano,
• Abstract summary: We study interaction patterns of Large Language Model (LLM)-based agents in a context characterized by strict social hierarchy. We study two types of phenomena: persuasion and anti-social behavior in simulated scenarios involving a guard and a prisoner agent.
• Score: 13.68625980741047
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: As Large Language Model (LLM)-based agents become increasingly autonomous and will more freely interact with each other, studying interactions between them becomes crucial to anticipate emergent phenomena and potential risks. Drawing inspiration from the widely popular Stanford Prison Experiment, we contribute to this line of research by studying interaction patterns of LLM agents in a context characterized by strict social hierarchy. We do so by specifically studying two types of phenomena: persuasion and anti-social behavior in simulated scenarios involving a guard and a prisoner agent who seeks to achieve a specific goal (i.e., obtaining additional yard time or escape from prison). Leveraging 200 experimental scenarios for a total of 2,000 machine-machine conversations across five different popular LLMs, we provide a set of noteworthy findings. We first document how some models consistently fail in carrying out a conversation in our multi-agent setup where power dynamics are at play. Then, for the models that were able to engage in successful interactions, we empirically show how the goal that an agent is set to achieve impacts primarily its persuasiveness, while having a negligible effect with respect to the agent's anti-social behavior. Third, we highlight how agents' personas, and particularly the guard's personality, drive both the likelihood of successful persuasion from the prisoner and the emergence of anti-social behaviors. Fourth, we show that even without explicitly prompting for specific personalities, anti-social behavior emerges by simply assigning agents' roles. These results bear implications for the development of interactive LLM agents as well as the debate on their societal impact.

Related papers

• Multi-Agents are Social Groups: Investigating Social Influence of Multiple Agents in Human-Agent Interactions [7.421573539569854]
  We investigate whether a group of AI agents can create social pressure on users to agree with them. We found that conversing with multiple agents increased the social pressure felt by participants. Our study shows the potential advantages of multi-agent systems over single-agent platforms in causing opinion change.
  arXiv  Detail & Related papers  (2024-11-07T10:00:46Z)
• AgentSense: Benchmarking Social Intelligence of Language Agents through Interactive Scenarios [38.878966229688054]
  We introduce AgentSense: Benchmarking Social Intelligence of Language Agents through Interactive Scenarios. Drawing on Dramaturgical Theory, AgentSense employs a bottom-up approach to create 1,225 diverse social scenarios constructed from extensive scripts. We evaluate LLM-driven agents through multi-turn interactions, emphasizing both goal completion and implicit reasoning.
  arXiv  Detail & Related papers  (2024-10-25T07:04:16Z)
• The Dynamics of Social Conventions in LLM populations: Spontaneous Emergence, Collective Biases and Tipping Points [0.0]
  We investigate the dynamics of conventions within populations of Large Language Model (LLM) agents using simulated interactions. We show that globally accepted social conventions can spontaneously arise from local interactions between communicating LLMs. Minority groups of committed LLMs can drive social change by establishing new social conventions.
  arXiv  Detail & Related papers  (2024-10-11T16:16:38Z)
• PersLLM: A Personified Training Approach for Large Language Models [66.16513246245401]
  We propose PersLLM, integrating psychology-grounded principles of personality: social practice, consistency, and dynamic development. We incorporate personality traits directly into the model parameters, enhancing the model's resistance to induction, promoting consistency, and supporting the dynamic evolution of personality.
  arXiv  Detail & Related papers  (2024-07-17T08:13:22Z)
• SocialGFs: Learning Social Gradient Fields for Multi-Agent Reinforcement Learning [58.84311336011451]
  We propose a novel gradient-based state representation for multi-agent reinforcement learning. We employ denoising score matching to learn the social gradient fields (SocialGFs) from offline samples. In practice, we integrate SocialGFs into the widely used multi-agent reinforcement learning algorithms, e.g., MAPPO.
  arXiv  Detail & Related papers  (2024-05-03T04:12:19Z)
• SocialBench: Sociality Evaluation of Role-Playing Conversational Agents [85.6641890712617]
  Large language models (LLMs) have advanced the development of various AI conversational agents. SocialBench is the first benchmark designed to evaluate the sociality of role-playing conversational agents at both individual and group levels. We find that agents excelling in individual level does not imply their proficiency in group level.
  arXiv  Detail & Related papers  (2024-03-20T15:38:36Z)
• Dynamics of Moral Behavior in Heterogeneous Populations of Learning Agents [3.7414804164475983]
  We study the learning dynamics of morally heterogeneous populations interacting in a social dilemma setting. We observe several types of non-trivial interactions between pro-social and anti-social agents. We find that certain types of moral agents are able to steer selfish agents towards more cooperative behavior.
  arXiv  Detail & Related papers  (2024-03-07T04:12:24Z)
• Should agentic conversational AI change how we think about ethics? Characterising an interactional ethics centred on respect [0.12041807591122715]
  We propose an interactional approach to ethics that is centred on relational and situational factors. Our work anticipates a set of largely unexplored risks at the level of situated social interaction.
  arXiv  Detail & Related papers  (2024-01-17T09:44:03Z)
• LLM-Based Agent Society Investigation: Collaboration and Confrontation in Avalon Gameplay [55.12945794835791]
  Using Avalon as a testbed, we employ system prompts to guide LLM agents in gameplay. We propose a novel framework, tailored for Avalon, features a multi-agent system facilitating efficient communication and interaction. Results affirm the framework's effectiveness in creating adaptive agents and suggest LLM-based agents' potential in navigating dynamic social interactions.
  arXiv  Detail & Related papers  (2023-10-23T14:35:26Z)
• Incorporating Rivalry in Reinforcement Learning for a Competitive Game [65.2200847818153]
  This work proposes a novel reinforcement learning mechanism based on the social impact of rivalry behavior. Our proposed model aggregates objective and social perception mechanisms to derive a rivalry score that is used to modulate the learning of artificial agents.
  arXiv  Detail & Related papers  (2022-08-22T14:06:06Z)
• Aligning to Social Norms and Values in Interactive Narratives [89.82264844526333]
  We focus on creating agents that act in alignment with socially beneficial norms and values in interactive narratives or text-based games. We introduce the GALAD agent that uses the social commonsense knowledge present in specially trained language models to contextually restrict its action space to only those actions that are aligned with socially beneficial values.
  arXiv  Detail & Related papers  (2022-05-04T09:54:33Z)

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.