PIVOTSBench: Evaluating Fine-Grained Interpersonal Relationship Reasoning in Multimodal Large Language Models

ACL ARR 2026 January Submission164 Authors

Keywords: social intelligence, multimodal large language models, benchmark, evaluation

Abstract: Humans possess an innate ability to understand fine-grained interpersonal relationships, which is central to everyday social interactions. Although such reasoning is inherently multimodal, it remains largely unexplored by existing multimodal large language models (MLLMs). To address this gap, we introduce \textbf{PIVOTS}, the first benchmark built from Social-IQ 2.0 and YouTube data to evaluate MLLMs’ ability to predict bidirectional interpersonal relationship dimensions grounded in established psychology research. In addition, PIVOTS includes auxiliary tasks that assess models’ ability to identify and leverage the critical visual cues underlying such predictions. We evaluate both proprietary and open-source MLLMs and conduct detailed ablation studies to analyze the effects of visual modalities and explicit social role information in conversational utterances. We further examine how joint and pairwise prediction settings benefit MLLMs in scoring bidirectional PIVOTS dimensions.

Paper Type: Long

Research Area: Computational Social Science, Cultural Analytics, and NLP for Social Good

Research Area Keywords: human behavior analysis

Contribution Types: Data resources

Languages Studied: english

Submission Number: 164