Skip to content
TheChatArchiveThe Chat Archive
gpt-4o-search-preview· OpenAIHugging Face LMArena Search Arena 24K

I need a paper in the intersection of social cognition (psychology) and artificial…

From a Chatbot Arena battleThe same person sent this prompt to two anonymous models at once. Compare it with Perplexitysonar-reasoning-pro-high’s answer.
  1. User

    I need a paper in the intersection of social cognition (psychology) and artificial intelligence. give me some options.

  2. Assistant

    Here are some research papers that explore the intersection of social cognition in psychology and artificial intelligence:

    1. "Exploring Prosocial Irrationality for LLM Agents: A Social Cognition View" by Xuan Liu et al. (May 2024): This paper investigates how large language model (LLM) agents exhibit prosocial behaviors and cognitive biases similar to humans. The authors introduce CogMir, a framework that leverages LLMs' hallucination properties to assess and enhance their social intelligence through cognitive biases[1].

    2. "Evaluating and Modeling Social Intelligence: A Comparative Study of Human and AI Capabilities" by Junqi Wang et al. (May 2024): This study presents a benchmark for evaluating social intelligence in AI, comparing human and AI capabilities. The authors develop a theoretical framework for social dynamics and introduce evaluation tasks to assess social intelligence, revealing that humans outperform the latest GPT models in various aspects of social cognition[2].

    3. "Replicating Human Social Perception in Generative AI: Evaluating the Valence-Dominance Model" by Necdet Gurkan et al. (March 2025): This research examines whether multimodal generative AI systems can replicate the valence-dominance model of human social perception. The study finds that these AI systems can reproduce key aspects of human social perception, raising important questions about their implications for AI-driven decision-making and human-AI interactions[3].

    4. "Spontaneous Theory of Mind for Artificial Intelligence" by Nikolos Gurney et al. (February 2024): This paper contrasts prompted Theory of Mind (ToM) with spontaneous ToM in AI, arguing for a principled approach to studying and developing AI ToM. The authors suggest that a robust artificial social intelligence should respond to prompts and spontaneously engage in social reasoning[4].

    These papers provide insights into how AI systems can model and replicate aspects of human social cognition, contributing to the development of artificial social intelligence.

Responses were produced in different, uncontrolled contexts (system prompts, settings, prior turns). This is not a benchmark.