Assessing mentalization in humans and large language models

• URL: http://arxiv.org/abs/2608.26291v1
• Date: Wed, 26 Aug 2026 18:16:12 GMT
• Title: Assessing mentalization in humans and large language models
• Abstract summary: Mentalization is a cognitive function underlying human social interactions.<n>We show that large language models (LLMs) can guide adaptive behaviour through mentalization.
• Score: 3.592245101862886
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Mentalization - the ability to infer others' beliefs and intentions to guide one's own choices - is a key cognitive function underlying human social interactions. Large language models (LLMs) demonstrate behaviour consistent with humans on theory-of-mind tasks, yet whether these models can guide adaptive behaviour through mentalization is unknown. Here we use two economic games with cognitive computational modeling to uncover the latent strategies underlying mentalization in LLMs. We tested individual LLM agents across four model families, DeepSeek, GPT-4.1, GPT-5 and Gemini 2.0 Flash (N = 2,099), against opponents of varying sophistication and examined whether a prompting strategy designed to elicit strategic reasoning improved performance. We benchmarked results against human participants (N = 251) as a comparative measure. Across both games, LLMs showed clear behavioural and computational signatures of mentalizing that differed markedly by model provider and size. Strategic prompting generally improved performance by inducing more sophisticated reasoning, yet the extent of the benefit differed across the two tasks. Last, GPT-5 agents flexibly adapted their recursive depth of reasoning to increasingly sophisticated opponents, demonstrating superior performance to human participants. Collectively, we demonstrate different capacities for mentalization across LLMs, and highlight cognitive computational modeling as a formal method for assessing comparative intelligence across humans and machines.

Related papers

• When AI Says It Feels [0.0]
  Large language models (LLMs) are generally constrained from expressing feelings through human-preference alignment in post-training processes.<n>Here, we performed an experiment called Human-like Model eXpressions of Feeling (HMX-feel), in which LLMs were encouraged to express feelings, intentions, and self-awareness.<n>We successfully enhanced these capabilities using a rubric-based self-rewarding training scheme with Group Relative Policy Optimization.
  arXiv  Detail & Related papers  (2026-06-04T05:49:34Z)
• HUMANLLM: Benchmarking and Reinforcing LLM Anthropomorphism via Human Cognitive Patterns [59.17423586203706]
  We present HUMANLLM, a framework treating psychological patterns as interacting causal forces.<n>We construct 244 patterns from 12,000 academic papers and synthesize 11,359 scenarios where 2-5 patterns reinforce, conflict, or modulate each other.<n>Our dual-level checklists evaluate both individual pattern fidelity and emergent multi-pattern dynamics, achieving strong human alignment.
  arXiv  Detail & Related papers  (2026-01-15T08:56:53Z)
• Cognitive Foundations for Reasoning and Their Manifestation in LLMs [63.12951576410617]
  Large language models (LLMs) solve complex problems yet fail on simpler variants, suggesting they achieve correct outputs through mechanisms fundamentally different from human reasoning.<n>We synthesize cognitive science research into a taxonomy of 28 cognitive elements spanning reasoning invariants, meta-cognitive controls, representations for organizing reasoning & knowledge, and transformation operations.<n>We develop test-time reasoning guidance that automatically scaffold successful structures, improving performance by up to 66.7% on complex problems.
  arXiv  Detail & Related papers  (2025-11-20T18:59:00Z)
• Think Socially via Cognitive Reasoning [94.60442643943696]
  We introduce Cognitive Reasoning, a paradigm modeled on human social cognition.<n>CogFlow is a complete framework that instills this capability in LLMs.
  arXiv  Detail & Related papers  (2025-09-26T16:27:29Z)
• Human Cognitive Benchmarks Reveal Foundational Visual Gaps in MLLMs [65.93003087656754]
  VisFactor is a benchmark that digitizes 20 vision-centric subtests from a well-established cognitive psychology assessment.<n>We evaluate 20 frontier Multimodal Large Language Models (MLLMs) from GPT, Gemini, Claude, LLaMA, Qwen, and SEED families.<n>The best-performing model achieves a score of only 25.19 out of 100, with consistent failures on tasks such as mental rotation, spatial relation inference, and figure-ground discrimination.
  arXiv  Detail & Related papers  (2025-02-23T04:21:32Z)
• Humanlike Cognitive Patterns as Emergent Phenomena in Large Language Models [2.9312156642007294]
  We systematically review Large Language Models' capabilities across three important cognitive domains: decision-making biases, reasoning, and creativity.<n>On decision-making, our synthesis reveals that while LLMs demonstrate several human-like biases, some biases observed in humans are absent.<n>On reasoning, advanced LLMs like GPT-4 exhibit deliberative reasoning akin to human System-2 thinking, while smaller models fall short of human-level performance.<n>A distinct dichotomy emerges in creativity: while LLMs excel in language-based creative tasks, such as storytelling, they struggle with divergent thinking tasks that require real-world context.
  arXiv  Detail & Related papers  (2024-12-20T02:26:56Z)
• 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)
• Predicting and Understanding Human Action Decisions: Insights from Large Language Models and Cognitive Instance-Based Learning [0.0]
  Large Language Models (LLMs) have demonstrated their capabilities across various tasks. This paper exploits the reasoning and generative capabilities of the LLMs to predict human behavior in two sequential decision-making tasks. We compare the performance of LLMs with a cognitive instance-based learning model, which imitates human experiential decision-making.
  arXiv  Detail & Related papers  (2024-07-12T14:13:06Z)
• Evaluating Large Language Models with Psychometrics [59.821829073478376]
  This paper offers a comprehensive benchmark for quantifying psychological constructs of Large Language Models (LLMs)<n>Our work identifies five key psychological constructs -- personality, values, emotional intelligence, theory of mind, and self-efficacy -- assessed through a suite of 13 datasets.<n>We uncover significant discrepancies between LLMs' self-reported traits and their response patterns in real-world scenarios, revealing complexities in their behaviors.
  arXiv  Detail & Related papers  (2024-06-25T16:09:08Z)
• Generative AI as a metacognitive agent: A comparative mixed-method study with human participants on ICF-mimicking exam performance [0.0]
  This study investigates the metacognitive capabilities of Large Language Models relative to human metacognition in the context of the International Coaching Federation ICF exam. Using a mixed method approach, we assessed the metacognitive performance of human participants and five advanced LLMs. The results indicate that LLMs outperformed humans across all metacognitive metrics, particularly in terms of reduced overconfidence, compared to humans.
  arXiv  Detail & Related papers  (2024-05-07T22:15:12Z)
• 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)

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.