EmoLoom-2B: Fast Base-Model Screening for Emotion Classification and VAD with Lexicon-Weak Supervision and KV-Off Evaluation

TL;DR

EmoLoom-2B is a fast, reproducible pipeline that efficiently screens small language models for emotion and VAD prediction, incorporating novel regularizers and augmentation techniques for improved performance and fairness.

Contribution

It introduces a unified, protocol-faithful evaluation framework with novel regularizers and augmentation methods for emotion classification and VAD prediction using small language models.

Findings

Achieves strong performance on GoEmotions and EmpatheticDialogues datasets.

Demonstrates robust cross-corpus generalization on DailyDialog.

Provides a budget-aware, auditable screening pipeline for emotion models.

Abstract

We introduce EmoLoom-2B, a lightweight and reproducible pipeline that turns small language models under 2B parameters into fast screening candidates for joint emotion classification and Valence-Arousal-Dominance prediction. To ensure protocol-faithful and fair evaluation, we unify data loading, training, and inference under a single JSON input-output contract and remove avoidable variance by adopting KV-off decoding as the default setting. We incorporate two orthogonal semantic regularizers: a VAD-preserving constraint that aligns generated text with target VAD triples, and a lightweight external appraisal classifier that provides training-time guidance on goal attainment, controllability, certainty, and fairness without injecting long rationales. To improve polarity sensitivity, we introduce Valence Flip augmentation based on mirrored emotional pairs. During supervised fine-tuning, we apply A/B mixture sampling with entropy-aware temperature scheduling to balance coverage and convergence. Using Qwen-1.8B-Chat as the base model, EmoLoom-2B achieves strong performance on GoEmotions and EmpatheticDialogues, and demonstrates robust cross-corpus generalization on DailyDialog. The proposed recipe is budget-aware, auditable, and re-entrant, serving as a dependable screening pass before heavier training or multimodal fusion.