Neural Theory-of-Mind? On the Limits of Social Intelligence in Large LMs

• URL: http://arxiv.org/abs/2210.13312v2
• Date: Mon, 3 Apr 2023 15:26:20 GMT
• Title: Neural Theory-of-Mind? On the Limits of Social Intelligence in Large LMs
• Authors: Maarten Sap, Ronan LeBras, Daniel Fried, Yejin Choi
• Abstract summary: We show that one of today's largest language models lacks this kind of social intelligence out-of-the box. We conclude that person-centric NLP approaches might be more effective towards neural Theory of Mind.
• Score: 77.88043871260466
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Social intelligence and Theory of Mind (ToM), i.e., the ability to reason about the different mental states, intents, and reactions of all people involved, allow humans to effectively navigate and understand everyday social interactions. As NLP systems are used in increasingly complex social situations, their ability to grasp social dynamics becomes crucial. In this work, we examine the open question of social intelligence and Theory of Mind in modern NLP systems from an empirical and theory-based perspective. We show that one of today's largest language models (GPT-3; Brown et al., 2020) lacks this kind of social intelligence out-of-the box, using two tasks: SocialIQa (Sap et al., 2019), which measures models' ability to understand intents and reactions of participants of social interactions, and ToMi (Le et al., 2019), which measures whether models can infer mental states and realities of participants of situations. Our results show that models struggle substantially at these Theory of Mind tasks, with well-below-human accuracies of 55% and 60% on SocialIQa and ToMi, respectively. To conclude, we draw on theories from pragmatics to contextualize this shortcoming of large language models, by examining the limitations stemming from their data, neural architecture, and training paradigms. Challenging the prevalent narrative that only scale is needed, we posit that person-centric NLP approaches might be more effective towards neural Theory of Mind. In our updated version, we also analyze newer instruction tuned and RLFH models for neural ToM. We find that even ChatGPT and GPT-4 do not display emergent Theory of Mind; strikingly even GPT-4 performs only 60% accuracy on the ToMi questions related to mental states and realities.

Related papers

• Learning mental states estimation through self-observation: a developmental synergy between intentions and beliefs representations in a deep-learning model of Theory of Mind [0.35154948148425685]
  Theory of Mind (ToM) is the ability to attribute beliefs, intentions, or mental states to others. We show a developmental synergy between learning to predict low-level mental states and attributing high-level ones. We propose that our computational approach can inform the understanding of human social cognitive development.
  arXiv  Detail & Related papers  (2024-07-25T13:15:25Z)
• OpenToM: A Comprehensive Benchmark for Evaluating Theory-of-Mind Reasoning Capabilities of Large Language Models [17.042114879350788]
  Neural Theory-of-Mind (N-ToM) machine's ability to understand and keep track of the mental states of others is pivotal in developing socially intelligent agents. OpenToM is a new benchmark for assessing N-ToM with longer and clearer narrative stories, explicit personality traits, and actions triggered by character intentions. We reveal that state-of-the-art LLMs thrive at modeling certain aspects of mental states in the physical world but fall short when tracking characters' mental states in the psychological world.
  arXiv  Detail & Related papers  (2024-02-08T20:35:06Z)
• Think Twice: Perspective-Taking Improves Large Language Models' Theory-of-Mind Capabilities [63.90227161974381]
  SimToM is a novel prompting framework inspired by Simulation Theory's notion of perspective-taking. Our approach, which requires no additional training and minimal prompt-tuning, shows substantial improvement over existing methods.
  arXiv  Detail & Related papers  (2023-11-16T22:49:27Z)
• Mindstorms in Natural Language-Based Societies of Mind [110.05229611910478]
  Minsky's "society of mind" and Schmidhuber's "learning to think" inspire diverse societies of large multimodal neural networks (NNs) Recent implementations of NN-based societies of minds consist of large language models (LLMs) and other NN-based experts communicating through a natural language interface. In these natural language-based societies of mind (NLSOMs), new agents -- all communicating through the same universal symbolic language -- are easily added in a modular fashion.
  arXiv  Detail & Related papers  (2023-05-26T16:21:25Z)
• COKE: A Cognitive Knowledge Graph for Machine Theory of Mind [87.14703659509502]
  Theory of mind (ToM) refers to humans' ability to understand and infer the desires, beliefs, and intentions of others. COKE is the first cognitive knowledge graph for machine theory of mind.
  arXiv  Detail & Related papers  (2023-05-09T12:36:58Z)
• Machine Psychology [54.287802134327485]
  We argue that a fruitful direction for research is engaging large language models in behavioral experiments inspired by psychology. We highlight theoretical perspectives, experimental paradigms, and computational analysis techniques that this approach brings to the table. It paves the way for a "machine psychology" for generative artificial intelligence (AI) that goes beyond performance benchmarks.
  arXiv  Detail & Related papers  (2023-03-24T13:24:41Z)
• Memory-Augmented Theory of Mind Network [59.9781556714202]
  Social reasoning requires the capacity of theory of mind (ToM) to contextualise and attribute mental states to others. Recent machine learning approaches to ToM have demonstrated that we can train the observer to read the past and present behaviours of other agents. We tackle the challenges by equipping the observer with novel neural memory mechanisms to encode, and hierarchical attention to selectively retrieve information about others. This results in ToMMY, a theory of mind model that learns to reason while making little assumptions about the underlying mental processes.
  arXiv  Detail & Related papers  (2023-01-17T14:48:58Z)
• Social Neuro AI: Social Interaction as the "dark matter" of AI [0.0]
  We argue that empirical results from social psychology and social neuroscience along with the framework of dynamics can be of inspiration to the development of more intelligent artificial agents.
  arXiv  Detail & Related papers  (2021-12-31T13:41:53Z)

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.