The field of artificial intelligence is moving towards developing more emotionally intelligent systems that can understand and respond to human emotions. Recent research has focused on creating models that can recognize and generate emotional cues, such as facial expressions, tone of voice, and language. These systems have the potential to improve human-computer interaction, particularly in applications such as chatbots, virtual assistants, and social robots. Notable papers in this area include: Being Kind Isn't Always Being Safe: Diagnosing Affective Hallucination in LLMs, which introduces a benchmark for diagnosing affective hallucination in large language models. EmoCAST: Emotional Talking Portrait via Emotive Text Description, which proposes a diffusion-based framework for generating talking portrait videos with vivid emotional expressions. ChatThero: An LLM-Supported Chatbot for Behavior Change and Therapeutic Support in Addiction Recovery, which presents a conversational framework that couples dynamic patient modeling with context-sensitive therapeutic dialogue and adaptive persuasive strategies.
Emotion-Aware AI Systems for Human Interaction
Sources
Seeing is Believing: Emotion-Aware Audio-Visual Language Modeling for Expressive Speech Generation
SafeSpace: An Integrated Web Application for Digital Safety and Emotional Well-being
RoboBuddy in the Classroom: Exploring LLM-Powered Social Robots for Storytelling in Learning and Integration Activities
Being Kind Isn't Always Being Safe: Diagnosing Affective Hallucination in LLMs
Social-MAE: A Transformer-Based Multimodal Autoencoder for Face and Voice
Emotion Omni: Enabling Empathetic Speech Response Generation through Large Language Models
Sense of Self and Time in Borderline Personality. A Comparative Robustness Study with Generative AI
Emotion Transfer with Enhanced Prototype for Unseen Emotion Recognition in Conversation
MathBuddy: A Multimodal System for Affective Math Tutoring
EmoCAST: Emotional Talking Portrait via Emotive Text Description
Schema-Guided Response Generation using Multi-Frame Dialogue State for Motivational Interviewing Systems
Feel the Difference? A Comparative Analysis of Emotional Arcs in Real and LLM-Generated CBT Sessions
ChatThero: An LLM-Supported Chatbot for Behavior Change and Therapeutic Support in Addiction Recovery