The field of artificial intelligence is moving towards developing more emotionally intelligent systems, with a focus on cognitive appraisal, emotional reasoning, and human-AI interaction. Recent studies have investigated the ability of large language models to recognize and respond to emotions, with some models showing promising results in tasks such as emotion detection and empathy. However, challenges remain, including the need for more nuanced and context-dependent emotional understanding, as well as the potential risks and biases associated with emotionally intelligent AI systems. Noteworthy papers in this area include 'Do Machines Think Emotionally?' which introduces a benchmark for evaluating cognitive reasoning for emotions in large language models, and 'EICAP' which presents a unified framework for assessing and enhancing emotional intelligence in large language models.
Emotional Intelligence in AI: Advances and Challenges
Sources
Do Machines Think Emotionally? Cognitive Appraisal Analysis of Large Language Models
EICAP: Deep Dive in Assessment and Enhancement of Large Language Models in Emotional Intelligence through Multi-Turn Conversations
Cyberbullying Detection via Aggression-Enhanced Prompting
Towards Safer AI Moderation: Evaluating LLM Moderators Through a Unified Benchmark Dataset and Advocating a Human-First Approach
Heartificial Intelligence: Exploring Empathy in Language Models
Between Fear and Desire, the Monster Artificial Intelligence (AI): Analysis through the Lenses of Monster Theory
UWB at WASSA-2024 Shared Task 2: Cross-lingual Emotion Detection
Silicon Minds versus Human Hearts: The Wisdom of Crowds Beats the Wisdom of AI in Emotion Recognition
MME-Emotion: A Holistic Evaluation Benchmark for Emotional Intelligence in Multimodal Large Language Models
The PacifAIst Benchmark:Would an Artificial Intelligence Choose to Sacrifice Itself for Human Safety?
INTIMA: A Benchmark for Human-AI Companionship Behavior
Automated scoring of the Ambiguous Intentions Hostility Questionnaire using fine-tuned large language models
Cognitive Cybersecurity for Artificial Intelligence: Guardrail Engineering with CCS-7
Artificial Emotion: A Survey of Theories and Debates on Realising Emotion in Artificial Intelligence