# Towards a Generative Approach for Emotion Detection and Reasoning

arXiv: https://arxiv.org/abs/2408.04906 · HTML: https://mlsanity.com/paper/2408.04906/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Audio-language model reasoning, one of 17 directions in LLM reasoning.
- Builds on 6 of its 34 references that are in the map.
- First posted on arXiv 9 Aug 2024.

## Placed in

- LLM reasoning / [Audio-language model reasoning](https://mlsanity.com/lr/audio-language-model-reasoning/)

## Builds on (most cited first, 6 of 6)

- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [A Survey of Hallucination in Large Foundation Models](https://mlsanity.com/paper/2309.05922/) (2023)
- [Benchmarking Zero-shot Text Classification: Datasets, Evaluation and Entailment Approach](https://mlsanity.com/paper/1909.00161/) (2019)
- [Towards Interpretable Mental Health Analysis with Large Language Models](https://mlsanity.com/paper/2304.03347/) (2023)
- [Cross Domain Emotion Recognition using Few Shot Knowledge Transfer](https://mlsanity.com/paper/2110.05021/) (2021)

## Built on by (most cited first, 3 of 3)

- [Figurative-cum-Commonsense Knowledge Infusion for Multimodal Mental Health Meme Classification](https://mlsanity.com/paper/2501.15321/) (2025)
- [From Joy to Fear: A Benchmark of Emotion Estimation in Pop Song Lyrics](https://mlsanity.com/paper/2509.05617/) (2025)
- [Contrastive Distillation of Emotion Knowledge from LLMs for Zero-Shot Emotion Recognition](https://mlsanity.com/paper/2505.18040/) (2025)

## Abstract (arXiv)

Large language models (LLMs) have demonstrated impressive performance in mathematical and commonsense reasoning tasks using chain-of-thought (CoT) prompting techniques. But can they perform emotional reasoning by concatenating `Let's think step-by-step' to the input prompt? In this paper we investigate this question along with introducing a novel approach to zero-shot emotion detection and emotional reasoning using LLMs. Existing state of the art zero-shot approaches rely on textual entailment models to choose the most appropriate emotion label for an input text. We argue that this strongly restricts the model to a fixed set of labels which may not be suitable or sufficient for many applications where emotion analysis is required. Instead, we propose framing the problem of emotion analysis as a generative question-answering (QA) task. Our approach uses a two step methodology of generating relevant context or background knowledge to answer the emotion detection question step-by-step. Our paper is the first work on using a generative approach to jointly address the tasks of emotion detection and emotional reasoning for texts. We evaluate our approach on two popular emotion detection datasets and also release the fine-grained emotion labels and explanations for further training and fine-tuning of emotional reasoning systems.