MoCA: Implicit Social Context Analysis

• URL: http://arxiv.org/abs/2608.05825v2
• Date: Fri, 07 Aug 2026 10:39:57 GMT
• Title: MoCA: Implicit Social Context Analysis
• Abstract summary: Implicit social contexts are pervasive in real-world interactions.<n>We introduce Implicit Social Context Analysis (MoCA), a novel task that systematically models implicit social scenarios.<n>We propose Conflict-Driven Abductive Reasoning (CoDAR), a novel framework that models the discrepancy between observed expressions and expected truthful behavior as cognitive conflict.
• Score: 36.39584457494872
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Human social communication, such as affection and intent, is often conveyed in highly implicit ways, where underlying meanings are expressed through indirect, socially and culturally grounded signals rather than explicit statements. Such implicit social contexts are pervasive in real-world interactions, yet there remains a lack of a formal and systematic framework for studying them. In this paper, we introduce Implicit Social Context Analysis (MoCA), a novel task that systematically models implicit social scenarios along three key dimensions: affection, intent, and stance. We construct a high-quality benchmark containing 3,108 multimodal instances collected from real-world sources, with fine-grained cognitive annotations revealing who expresses what toward whom, as well as how and why it is conveyed. Using the MoCA dataset, we show that state-of-the-art multimodal large language models struggle significantly with this task because of their reliance on explicit cues and limited ability to reason over latent social contexts. To address this challenge, we propose Conflict-Driven Abductive Reasoning (CoDAR), a novel framework that models the discrepancy between observed expressions and expected truthful behavior as cognitive conflict, thereby enabling the inference of hidden mental states. Extensive experiments demonstrate that CoDAR substantially improves model performance. Nevertheless, a large gap from human reasoning remains, highlighting the fundamental difficulty of implicit social understanding.

Related papers

• SocialOmni: Benchmarking Audio-Visual Social Interactivity in Omni Models [86.19617358080016]
  Social Omni is a benchmark that operationalizes the evaluation of conversational interactivity across three core dimensions.<n>Social Omni features 2,000 perception samples and a quality-controlled diagnostic set of 209 interaction-generation instances.<n>Our analysis reveals a pronounced decoupling between a model's perceptual accuracy and its ability to generate contextually appropriate interruptions.
  arXiv  Detail & Related papers  (2026-03-17T17:58:44Z)
• Social-R1: Towards Human-like Social Reasoning in LLMs [74.32494331695837]
  We argue that cultivating human-like social intelligence requires training with challenging cases that resist shortcut solutions.<n>We propose Social-R1, a reinforcement learning framework that aligns model reasoning with human cognition through multi-dimensional rewards.
  arXiv  Detail & Related papers  (2026-03-10T06:26:24Z)
• A Scoping Review of the Ethical Perspectives on Anthropomorphising Large Language Model-Based Conversational Agents [39.49473274097833]
  Anthropomorphisation -- whereby non-human entities are ascribed human-like qualities -- has become increasingly salient with the rise of large language model (LLM)-based conversational agents (CAs)<n>This scoping review maps ethically oriented work on anthropomorphising LLM-based CAs across five databases and three preprint repositories.
  arXiv  Detail & Related papers  (2026-01-14T21:03:11Z)
• S$^3$IT: A Benchmark for Spatially Situated Social Intelligence Test [26.79990069295221]
  We introduce the Spatially Situated Social Intelligence Test (S$3$IT), a benchmark specifically designed to evaluate embodied social intelligence.<n>It is centered on a novel and challenging seat-ordering task, requiring an agent to arrange seating in a 3D environment for a group of large language model-driven NPCs.<n>Our framework generates a vast and diverse scenario space with controllable difficulty, compelling the agent to acquire preferences through active dialogue, perceive the environment via autonomous exploration, and perform multi-objective optimization within a complex constraint network.
  arXiv  Detail & Related papers  (2025-12-23T02:36:56Z)
• SocialNLI: A Dialogue-Centric Social Inference Dataset [49.60157928163403]
  We introduce SocialNLI -- the first social dialogue inference dataset.<n>SocialNLI consists of a collection of dialogue transcripts hand-picked to center complex social nuances.<n>We evaluate reasoning models theory-of-mind ability through multi-step counterfactual reasoning.
  arXiv  Detail & Related papers  (2025-10-06T23:42:01Z)
• SocialMaze: A Benchmark for Evaluating Social Reasoning in Large Language Models [41.68365456601248]
  We introduce SocialMaze, a new benchmark specifically designed to evaluate social reasoning.<n>SocialMaze systematically incorporates three core challenges: deep reasoning, dynamic interaction, and information uncertainty.<n>It provides six diverse tasks across three key settings: social reasoning games, daily-life interactions, and digital community platforms.
  arXiv  Detail & Related papers  (2025-05-29T17:47:36Z)
• Analyzing Cognitive Differences Among Large Language Models through the Lens of Social Worldview [39.19508676240209]
  We introduce the Social Worldview Taxonomy (SWT), a structured framework grounded in Cultural Theory.<n>We empirically identify distinct and interpretable cognitive profiles across 28 diverse Large Language Models.<n>Our findings enhance the interpretability of LLMs by revealing implicit socio-cognitive biases and their responsiveness to social feedback.
  arXiv  Detail & Related papers  (2025-05-04T02:35:24Z)
• Social Genome: Grounded Social Reasoning Abilities of Multimodal Models [61.88413918026431]
  Social reasoning abilities are crucial for AI systems to interpret and respond to multimodal human communication and interaction within social contexts.<n>We introduce SOCIAL GENOME, the first benchmark for fine-grained, grounded social reasoning abilities of multimodal models.
  arXiv  Detail & Related papers  (2025-02-21T00:05:40Z)
• DiPlomat: A Dialogue Dataset for Situated Pragmatic Reasoning [89.92601337474954]
  Pragmatic reasoning plays a pivotal role in deciphering implicit meanings that frequently arise in real-life conversations. We introduce a novel challenge, DiPlomat, aiming at benchmarking machines' capabilities on pragmatic reasoning and situated conversational understanding.
  arXiv  Detail & Related papers  (2023-06-15T10:41:23Z)
• ECHo: A Visio-Linguistic Dataset for Event Causality Inference via Human-Centric Reasoning [22.951360187153156]
  ECHo is a dataset of event causality inference grounded in visio-linguistic social scenarios. We propose a unified Chain-of-Thought (CoT) framework to assess the reasoning capability of current AI systems.
  arXiv  Detail & Related papers  (2023-05-24T05:21:13Z)

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.