TinyEmo: Scaling down Emotional Reasoning via Metric Projection
Cristian Gutierrez

TL;DR
TinyEmo introduces a compact multi-modal emotional reasoning model that leverages a novel metric projector for efficient classification, interpretability, and bias detection, outperforming larger models on emotion tasks.
Contribution
The paper presents TinyEmo, a small multi-modal language model with a metric projector for efficient emotional reasoning and bias detection, enabling high performance with fewer parameters.
Findings
Small models outperform larger ones on emotion classification.
The metric projector enhances interpretability and bias detection.
TinyEmo achieves strong results with only 700M parameters.
Abstract
This paper introduces TinyEmo, a family of small multi-modal language models for emotional reasoning and classification. Our approach features: (1) a synthetic emotional instruct dataset for both pre-training and fine-tuning stages, (2) a Metric Projector that delegates classification from the language model allowing for more efficient training and inference, (3) a multi-modal large language model (MM-LLM) for emotional reasoning, and (4) a semi-automated framework for bias detection. TinyEmo is able to perform emotion classification and emotional reasoning, all while using substantially fewer parameters than comparable models. This efficiency allows us to freely incorporate more diverse emotional datasets, enabling strong performance on classification tasks, with our smallest model (700M parameters) outperforming larger state-of-the-art models based on general-purpose MM-LLMs with over…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsTopic Modeling · Intelligent Tutoring Systems and Adaptive Learning · Multimodal Machine Learning Applications
