# Contrastive Distillation of Emotion Knowledge from LLMs for Zero-Shot Emotion Recognition

arXiv: https://arxiv.org/abs/2505.18040 · HTML: https://mlsanity.com/paper/2505.18040/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 27 of its 51 references that are in the map.
- First posted on arXiv 23 May 2025.

## Builds on (most cited first, 27 of 27)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [GoEmotions: A Dataset of Fine-Grained Emotions](https://mlsanity.com/paper/2005.00547/) (2020)
- [Benchmarking Zero-shot Text Classification: Datasets, Evaluation and Entailment Approach](https://mlsanity.com/paper/1909.00161/) (2019)
- [Sentiment Analysis in the Era of Large Language Models: A Reality Check](https://mlsanity.com/paper/2305.15005/) (2023)
- [Dawn of the transformer era in speech emotion recognition: closing the valence gap](https://mlsanity.com/paper/2203.07378/) (2022)
- [Rule Based Rewards for Language Model Safety](https://mlsanity.com/paper/2411.01111/) (2024)
- [A Review on Edge Large Language Models: Design, Execution, and Applications](https://mlsanity.com/paper/2410.11845/) (2024)
- [Investigating Bias and Fairness in Facial Expression Recognition](https://mlsanity.com/paper/2007.10075/) (2020)
- [FOFO: A Benchmark to Evaluate LLMs' Format-Following Capability](https://mlsanity.com/paper/2402.18667/) (2024)
- [EmoBank: Studying the Impact of Annotation Perspective and Representation Format on Dimensional Emotion Analysis](https://mlsanity.com/paper/2205.01996/) (2022)
- [EmoLLMs: A Series of Emotional Large Language Models and Annotation Tools for Comprehensive Affective Analysis](https://mlsanity.com/paper/2401.08508/) (2024)
- [GPT-4V with Emotion: A Zero-shot Benchmark for Generalized Emotion Recognition](https://mlsanity.com/paper/2312.04293/) (2023)
- [Utilizing Neural Networks and Linguistic Metadata for Early Detection of Depression Indications in Text Sequences](https://mlsanity.com/paper/1804.07000/) (2018)
- [OV-MER: Towards Open-Vocabulary Multimodal Emotion Recognition](https://mlsanity.com/paper/2410.01495/) (2024)
- [GPT-4 Emulates Average-Human Emotional Cognition from a Third-Person Perspective](https://mlsanity.com/paper/2408.13718/) (2024)
- [Natural Language Inference Prompts for Zero-shot Emotion Classification in Text across Corpora](https://mlsanity.com/paper/2209.06701/) (2022)
- [From Text to Emotion: Unveiling the Emotion Annotation Capabilities of LLMs](https://mlsanity.com/paper/2408.17026/) (2024)
- [Multitask Multi-database Emotion Recognition](https://mlsanity.com/paper/2107.04127/) (2021)
- [Affective Computing for Healthcare: Recent Trends, Applications, Challenges, and Beyond](https://mlsanity.com/paper/2402.13589/) (2024)
- [Towards Label-Agnostic Emotion Embeddings](https://mlsanity.com/paper/2012.00190/) (2020)
- [Using Emotion Embeddings to Transfer Knowledge Between Emotions, Languages, and Annotation Formats](https://mlsanity.com/paper/2211.00171/) (2022)
- [English Prompts are Better for NLI-based Zero-Shot Emotion Classification than Target-Language Prompts](https://mlsanity.com/paper/2402.03223/) (2024)
- [Emo Pillars: Knowledge Distillation to Support Fine-Grained Context-Aware and Context-Less Emotion Classification](https://mlsanity.com/paper/2504.16856/) (2025)
- [Towards a Generative Approach for Emotion Detection and Reasoning](https://mlsanity.com/paper/2408.04906/) (2024)
- [Cross Domain Emotion Recognition using Few Shot Knowledge Transfer](https://mlsanity.com/paper/2110.05021/) (2021)

## Abstract (arXiv)

The ability to handle various emotion labels without dedicated training is crucial for building adaptable Emotion Recognition (ER) systems. Conventional ER models rely on training using fixed label sets and struggle to generalize beyond them. On the other hand, Large Language Models (LLMs) have shown strong zero-shot ER performance across diverse label spaces, but their scale limits their use on edge devices. In this work, we propose a contrastive distillation framework that transfers rich emotional knowledge from LLMs into a compact model without the use of human annotations. We use GPT-4 to generate descriptive emotion annotations, offering rich supervision beyond fixed label sets. By aligning text samples with emotion descriptors in a shared embedding space, our method enables zero-shot prediction on different emotion classes, granularity, and label schema. The distilled model is effective across multiple datasets and label spaces, outperforming strong baselines of similar size and approaching GPT-4's zero-shot performance, while being over 10,000 times smaller.