SoMi-ToM: Evaluating Multi-Perspective Theory of Mind in Embodied Social Interactions

• URL: http://arxiv.org/abs/2506.23046v1
• Date: Sun, 29 Jun 2025 00:54:13 GMT
• Title: SoMi-ToM: Evaluating Multi-Perspective Theory of Mind in Embodied Social Interactions
• Authors: Xianzhe Fan, Xuhui Zhou, Chuanyang Jin, Kolby Nottingham, Hao Zhu, Maarten Sap,
• Abstract summary: SoMi-ToM benchmark is designed to evaluate multi-perspective ToM in embodied multi-agent complex social interactions.<n>We constructed a challenging dataset containing 35 third-person perspective videos, 363 first-person perspective images, and 1225 expert-annotated multiple-choice questions.<n>Results show that LVLMs perform significantly worse than humans on SoMi-ToM.
• Score: 21.149270997910403
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Humans continuously infer the states, goals, and behaviors of others by perceiving their surroundings in dynamic, real-world social interactions. However, most Theory of Mind (ToM) benchmarks only evaluate static, text-based scenarios, which have a significant gap compared to real interactions. We propose the SoMi-ToM benchmark, designed to evaluate multi-perspective ToM in embodied multi-agent complex social interactions. This benchmark is based on rich multimodal interaction data generated by the interaction environment SoMi, covering diverse crafting goals and social relationships. Our framework supports multi-level evaluation: (1) first-person evaluation provides multimodal (visual, dialogue, action, etc.) input from a first-person perspective during a task for real-time state inference, (2) third-person evaluation provides complete third-person perspective video and text records after a task for goal and behavior inference. This evaluation method allows for a more comprehensive examination of a model's ToM capabilities from both the subjective immediate experience and the objective global observation. We constructed a challenging dataset containing 35 third-person perspective videos, 363 first-person perspective images, and 1225 expert-annotated multiple-choice questions (three options). On this dataset, we systematically evaluated the performance of human subjects and several state-of-the-art large vision-language models (LVLMs). The results show that LVLMs perform significantly worse than humans on SoMi-ToM: the average accuracy gap between humans and models is 40.1% in first-person evaluation and 26.4% in third-person evaluation. This indicates that future LVLMs need to further improve their ToM capabilities in embodied, complex social interactions.

Related papers

• HV-MMBench: Benchmarking MLLMs for Human-Centric Video Understanding [79.06209664703258]
  Multimodal Large Language Models (MLLMs) have demonstrated significant advances in visual understanding tasks involving both images and videos.<n>Existing human-centric benchmarks predominantly emphasize video generation quality and action recognition, while overlooking essential perceptual and cognitive abilities required in human-centered scenarios.<n>We propose a rigorously curated benchmark designed to provide a more holistic evaluation of MLLMs in human-centric video understanding.
  arXiv  Detail & Related papers  (2025-07-07T11:52:24Z)
• VisuLogic: A Benchmark for Evaluating Visual Reasoning in Multi-modal Large Language Models [121.03333569013148]
  We introduce VisuLogic: a benchmark of 1,000 human-verified problems across six categories.<n>These types of questions can be evaluated to assess the visual reasoning capabilities of MLLMs from multiple perspectives.<n>Most models score below 30% accuracy-only slightly above the 25% random baseline and far below the 51.4% achieved by humans.
  arXiv  Detail & Related papers  (2025-04-21T17:59:53Z)
• Judge Anything: MLLM as a Judge Across Any Modality [43.51517213949702]
  This paper introduces two benchmarks, TaskAnything and JudgeAnything, to evaluate the overall performance and judging capabilities of MLLMs across any-to-any modality tasks.<n> TaskAnything evaluates the MMU and MMG capabilities across 15 any-to-any modality categories, employing 1,500 queries curated from well-established benchmarks.<n>JudgeAnything evaluates the judging capabilities of 5 advanced (e.g., GPT-4o and Gemini-2.0-Flash) from the perspectives of Pair Comparison and Score Evaluation.<n>Our work highlights the need for fairer evaluation protocols and stronger alignment with human preferences.
  arXiv  Detail & Related papers  (2025-03-21T18:59:20Z)
• 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)
• MMIE: Massive Multimodal Interleaved Comprehension Benchmark for Large Vision-Language Models [71.36392373876505]
  We introduce MMIE, a large-scale benchmark for evaluating interleaved multimodal comprehension and generation in Large Vision-Language Models (LVLMs)<n>MMIE comprises 20K meticulously curated multimodal queries, spanning 3 categories, 12 fields, and 102 subfields, including mathematics, coding, physics, literature, health, and arts.<n>It supports both interleaved inputs and outputs, offering a mix of multiple-choice and open-ended question formats to evaluate diverse competencies.
  arXiv  Detail & Related papers  (2024-10-14T04:15:00Z)
• VHELM: A Holistic Evaluation of Vision Language Models [75.88987277686914]
  We present the Holistic Evaluation of Vision Language Models (VHELM) VHELM aggregates various datasets to cover one or more of the 9 aspects: visual perception, knowledge, reasoning, bias, fairness, multilinguality, robustness, toxicity, and safety. Our framework is designed to be lightweight and automatic so that evaluation runs are cheap and fast.
  arXiv  Detail & Related papers  (2024-10-09T17:46:34Z)
• Assessment of Multimodal Large Language Models in Alignment with Human Values [43.023052912326314]
  We introduce Ch3Ef, a Compreh3ensive Evaluation dataset and strategy for assessing alignment with human expectations. Ch3Ef dataset contains 1002 human-annotated data samples, covering 12 domains and 46 tasks based on the hhh principle.
  arXiv  Detail & Related papers  (2024-03-26T16:10:21Z)
• Evaluating Human-Language Model Interaction [79.33022878034627]
  We develop a new framework, Human-AI Language-based Interaction Evaluation (HALIE), that defines the components of interactive systems. We design five tasks to cover different forms of interaction: social dialogue, question answering, crossword puzzles, summarization, and metaphor generation. We find that better non-interactive performance does not always translate to better human-LM interaction.
  arXiv  Detail & Related papers  (2022-12-19T18:59:45Z)

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.