Retrieving Implicit and Explicit Emotional Events Using Large Language Models

TL;DR

This paper investigates the ability of large language models to retrieve implicit and explicit emotional events in commonsense scenarios, using a novel supervised contrastive probing method to evaluate their performance and diversity.

Contribution

It introduces a systematic evaluation framework for LLMs' emotion retrieval capabilities, highlighting their strengths and limitations in handling emotional information.

Findings

LLMs can retrieve both implicit and explicit emotional events with varying accuracy.

The proposed probing method effectively measures diversity and performance in emotion retrieval.

Results reveal specific strengths and limitations of current LLMs in emotional understanding.

Abstract

Large language models (LLMs) have garnered significant attention in recent years due to their impressive performance. While considerable research has evaluated these models from various perspectives, the extent to which LLMs can perform implicit and explicit emotion retrieval remains largely unexplored. To address this gap, this study investigates LLMs' emotion retrieval capabilities in commonsense. Through extensive experiments involving multiple models, we systematically evaluate the ability of LLMs on emotion retrieval. Specifically, we propose a supervised contrastive probing method to verify LLMs' performance for implicit and explicit emotion retrieval, as well as the diversity of the emotional events they retrieve. The results offer valuable insights into the strengths and limitations of LLMs in handling emotion retrieval.