# The Shape of Power: A Multilingual Framework for Social Power Reasoning in Dialogues

arXiv: https://arxiv.org/abs/2608.28144 · HTML: https://mlsanity.com/paper/2608.28144/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 8 of its 42 references that are in the map.
- First posted on arXiv 28 Aug 2026.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)

## Builds on (most cited first, 8 of 8)

- [Towards Measuring and Modeling "Culture" in LLMs: A Survey](https://mlsanity.com/paper/2403.15412/) (2024)
- [Molmo2: Open Weights and Data for Vision-Language Models with Video Understanding and Grounding](https://mlsanity.com/paper/2601.10611/) (2026)
- [A Computational Approach to Politeness with Application to Social Factors](https://mlsanity.com/paper/1306.6078/) (2013)
- [POTATO: The Portable Text Annotation Tool](https://mlsanity.com/paper/2212.08620/) (2022)
- [LightTag: Text Annotation Platform](https://mlsanity.com/paper/2109.02320/) (2021)
- [DiPlomat: A Dialogue Dataset for Situated Pragmatic Reasoning](https://mlsanity.com/paper/2306.09030/) (2023)
- [Hollywood Identity Bias Dataset: A Context Oriented Bias Analysis of Movie Dialogues](https://mlsanity.com/paper/2205.15951/) (2022)
- [Interface Design for Crowdsourcing Hierarchical Multi-Label Text Annotations](https://mlsanity.com/paper/2302.02990/) (2023)

## Abstract (arXiv)

Social power plays a fundamental role in shaping human interaction, yet computational studies of power remain limited to narrow linguistic and cultural settings. Existing datasets further lack the demographic and relational depth needed for robust cross-cultural analysis. To address this gap, we introduce a theoretically grounded framework for studying social power in naturalistic multilingual dialogue through movie screenplays. The framework integrates a schema informed by social science theory, a native speaker annotation pipeline refined through pilot studies, and a custom interface for scalable cross-lingual analysis. Using this framework, we constructed an initial corpus containing 15,836 annotated instances from 100 scenes in French and Egyptian Arabic movies. Our analysis reveals strong agreement on observable demographic and contextual attributes, while socially interpretive aspects, such as power asymmetry and intention alignment, remain more contested, highlighting the complexity of social power across cultures. We evaluated 6 Large Language Models (LLMs) and Multimodal LLMs on cross-cultural social power reasoning, finding persistent gaps between human and model agreement in relational and theory-of-mind reasoning. Our work introduces the first extensible multilingual framework for studying social power in dialogues and provides an initial evaluation setting for studying cross-cultural social reasoning.