On Emergent Social World Models -- Evidence for Functional Integration of Theory of Mind and Pragmatic Reasoning in Language Models

• URL: http://arxiv.org/abs/2602.10298v1
• Date: Tue, 10 Feb 2026 21:12:12 GMT
• Title: On Emergent Social World Models -- Evidence for Functional Integration of Theory of Mind and Pragmatic Reasoning in Language Models
• Authors: Polina Tsvilodub, Jan-Felix Klumpp, Amir Mohammadpour, Jennifer Hu, Michael Franke,
• Abstract summary: This paper investigates whether LMs recruit shared computational mechanisms for general Theory of Mind (ToM) and language-specific pragmatic reasoning.<n>We analyze LMs' performance across seven subcategories of ToM abilities on a substantially larger localizer dataset.<n>Results from stringent hypothesis-driven statistical testing offer suggestive evidence for the functional integration hypothesis.
• Score: 4.5373666852176715
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This paper investigates whether LMs recruit shared computational mechanisms for general Theory of Mind (ToM) and language-specific pragmatic reasoning in order to contribute to the general question of whether LMs may be said to have emergent "social world models", i.e., representations of mental states that are repurposed across tasks (the functional integration hypothesis). Using behavioral evaluations and causal-mechanistic experiments via functional localization methods inspired by cognitive neuroscience, we analyze LMs' performance across seven subcategories of ToM abilities (Beaudoin et al., 2020) on a substantially larger localizer dataset than used in prior like-minded work. Results from stringent hypothesis-driven statistical testing offer suggestive evidence for the functional integration hypothesis, indicating that LMs may develop interconnected "social world models" rather than isolated competencies. This work contributes novel ToM localizer data, methodological refinements to functional localization techniques, and empirical insights into the emergence of social cognition in artificial systems.

Related papers

• Beyond Words: Evaluating and Bridging Epistemic Divergence in User-Agent Interaction via Theory of Mind [8.740788873949471]
  Large Language Models (LLMs) have developed rapidly and are widely applied to both general-purpose and professional tasks.<n>They still struggle to comprehend and respond to the true user needs when intentions and instructions are imprecisely conveyed.
  arXiv  Detail & Related papers  (2026-02-14T16:01:59Z)
• Investigating The Functional Roles of Attention Heads in Vision Language Models: Evidence for Reasoning Modules [76.21320451720764]
  We introduce CogVision, a dataset that decomposes complex multimodal questions into step-by-step subquestions.<n>Using a probing-based methodology, we identify attention heads that specialize in these functions and characterize them as functional heads.<n>Our analysis reveals that these functional heads are universally sparse, vary in number and distribution across functions, and mediate interactions and hierarchical organization.
  arXiv  Detail & Related papers  (2025-12-11T05:42:53Z)
• The Qualitative Laboratory: Theory Prototyping and Hypothesis Generation with Large Language Models [0.0]
  We argue that for this specific task, persona simulation offers a distinct advantage over established methods.<n>By generating naturalistic discourse, it overcomes the lack of discursive depth common in vignette surveys.<n>We present a protocol where personas derived from a sociological theory of climate reception react to policy messages.
  arXiv  Detail & Related papers  (2025-11-25T08:31:48Z)
• Social World Model-Augmented Mechanism Design Policy Learning [58.739456918502704]
  We introduce SWM-AP (Social World Model-Augmented Mechanism Design Policy Learning), which learns a social world model hierarchically to enhance mechanism design.<n>We show that SWM-AP outperforms established model-based and model-free RL baselines in cumulative rewards and sample efficiency.
  arXiv  Detail & Related papers  (2025-10-22T06:01:21Z)
• Doing Things with Words: Rethinking Theory of Mind Simulation in Large Language Models [48.815314312823006]
  This study explores whether the Generative Agent-Based Model (GABM) Concordia can effectively model Theory of Mind (ToM) within simulated real-world environments.<n>We assess whether this framework successfully simulates ToM abilities and whether GPT-4 can perform tasks by making genuine inferences from social context.
  arXiv  Detail & Related papers  (2025-10-15T10:48:31Z)
• Modeling Open-World Cognition as On-Demand Synthesis of Probabilistic Models [93.1043186636177]
  We explore the hypothesis that people use a combination of distributed and symbolic representations to construct bespoke mental models tailored to novel situations.<n>We propose a computational implementation of this idea -- a Model Synthesis Architecture''<n>We evaluate our MSA as a model of human judgments on a novel reasoning dataset.
  arXiv  Detail & Related papers  (2025-07-16T18:01:03Z)
• PersLLM: A Personified Training Approach for Large Language Models [66.16513246245401]
  We propose PersLLM, a framework for better data construction and model tuning.<n>For insufficient data usage, we incorporate strategies such as Chain-of-Thought prompting and anti-induction.<n>For rigid behavior patterns, we design the tuning process and introduce automated DPO to enhance the specificity and dynamism of the models' personalities.
  arXiv  Detail & Related papers  (2024-07-17T08:13:22Z)
• Exploring Collaboration Mechanisms for LLM Agents: A Social Psychology View [60.80731090755224]
  This paper probes the collaboration mechanisms among contemporary NLP systems by practical experiments with theoretical insights. We fabricate four unique societies' comprised of LLM agents, where each agent is characterized by a specific trait' (easy-going or overconfident) and engages in collaboration with a distinct thinking pattern' (debate or reflection) Our results further illustrate that LLM agents manifest human-like social behaviors, such as conformity and consensus reaching, mirroring social psychology theories.
  arXiv  Detail & Related papers  (2023-10-03T15:05:52Z)
• 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)
• Multi-Agent Inverse Reinforcement Learning: Suboptimal Demonstrations and Alternative Solution Concepts [0.0]
  Multi-agent inverse reinforcement learning can be used to learn reward functions from agents in social environments. To model realistic social dynamics, MIRL methods must account for suboptimal human reasoning and behavior.
  arXiv  Detail & Related papers  (2021-09-02T19:15:29Z)

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.