paper-with-me

홈 › Papers

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

2026-02-10 · Polina Tsvilodub, Jan-Felix Klumpp, Amir Mohammadpour, Jennifer Hu, Michael Franke arxiv

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.

📄 PDF Abstract BibTeX arXiv:2602.10298

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Emergent Relational Order in LLM Agent Societies: From Collective Affect to Authority Stratification

2026-06-22 · Zhiyuan Ji, Xinyu Chen, Ziqi Dai, Shiyun Tang 외 arxiv

Fei Xiaotong's Differential Order Pattern characterizes rural society as egocentric and relationally graded, with cooperation attenuating over social distance. Although often treated as culturally specific, its mechanist…

Emergent Reciprocity and Team Formation from Randomized Uncertain Social Preferences

2020-11-10 · NeurIPS 2020 12 · Bowen Baker

Multi-agent reinforcement learning (MARL) has shown recent success in increasingly complex fixed-team zero-sum environments. However, the real world is not zero-sum nor does it have fixed teams; humans face numerous soci…

Multi-agent Reinforcement Learning

A Mechanistic View on Video Generation as World Models: State and Dynamics

2026-01-22 · Luozhou Wang, Zhifei Chen, Yihua Du, Dongyu Yan 외 arxiv

Large-scale video generation models have demonstrated emergent physical coherence, positioning them as potential world models. However, a gap remains between contemporary "stateless" video architectures and classic state…

Video Generation

Emergent Road Rules In Multi-Agent Driving Environments

2020-11-21 · ICLR 2021 1 · Avik Pal, Jonah Philion, Yuan-Hong Liao, Sanja Fidler

For autonomous vehicles to safely share the road with human drivers, autonomous vehicles must abide by specific "road rules" that human drivers have agreed to follow. "Road rules" include rules that drivers are required …

Autonomous Vehicles

Do Large Language Models Solve the Problems of Agent-Based Modeling? A Critical Review of Generative Social Simulations

2025-04-04 · Maik Larooij, Petter Törnberg

Recent advancements in AI have reinvigorated Agent-Based Models (ABMs), as the integration of Large Language Models (LLMs) has led to the emergence of ``generative ABMs'' as a novel approach to simulating social systems.…