MTT-Bench: Predicting Social Dominance in Mice via Multimodal Large Language Models

TL;DR

This paper introduces MTT-Bench, a benchmark for analyzing mouse social dominance using multimodal large language models, demonstrating their ability to predict hierarchy from raw behavioral videos without domain-specific training.

Contribution

The work presents a novel benchmark and fine-tunes existing multimodal models for zero-shot social dominance prediction in mice from behavioral videos.

Findings

High agreement with tube test rankings

Effective zero-shot inference on unseen behaviors

Introduces a new direction for ethology analysis

Abstract

Understanding social dominance in animal behavior is critical for neuroscience and behavioral studies. In this work, we explore the capability of Multimodal Large Language Models(MLLMs) to analyze raw behavioral video of mice and predict their dominance hierarchy. We introduce MTT-Bench, a novel benchmark comprising annotated videos of pairwise mouse interactions for Mouse Tube Test analysis. Building on existing MLLM architectures, we fine-tune these models to perform zero-shot inference on unseen behavioral sequences, predicting social dominance without explicit labels during testing. Our framework demonstrates promising results, showing high agreement with tube test rankings. This work opens a new direction for applying foundation models to ethology and social behavior analysis, without the need to design domain-specific models.