The field of artificial intelligence is moving towards a more human-centric approach, with a focus on developing models that can understand and interact with humans in a more natural and intuitive way. Recent research has shown significant advancements in this area, with the development of models that can incorporate psychological theories and understand human emotions, behaviors, and mental states. Notable papers in this area include MultiMind, which enhances Werewolf agents with multimodal reasoning and Theory of Mind, and HyPerAlign, which proposes a novel interpretable and sample-efficient hypotheses-driven personalization approach for large language models. These advancements have the potential to improve human-AI interactions and enable the development of more sophisticated and human-like AI models.
Advancements in Human-Centric AI
Sources
Improving LLM Personas via Rationalization with Psychological Scaffolds
MultiMind: Enhancing Werewolf Agents with Multimodal Reasoning and Theory of Mind
Exploring Personality-Aware Interactions in Salesperson Dialogue Agents
TRACE Back from the Future: A Probabilistic Reasoning Approach to Controllable Language Generation
Can Third-parties Read Our Emotions?
The Convergent Ethics of AI? Analyzing Moral Foundation Priorities in Large Language Models with a Multi-Framework Approach
Real-Time Imitation of Human Head Motions, Blinks and Emotions by Nao Robot: A Closed-Loop Approach
BrAIcht, a theatrical agent that speaks like Bertolt Brecht's characters
Leveraging Systems and Control Theory for Social Robotics: A Model-Based Behavioral Control Approach to Human-Robot Interaction
MF-LLM: Simulating Collective Decision Dynamics via a Mean-Field Large Language Model Framework
Applying Machine Learning for characterizing social networks Agent-based models
The Mind in the Machine: A Survey of Incorporating Psychological Theories in LLMs
Theory of Mind in Large Language Models: Assessment and Enhancement
HyPerAlign: Hypotheses-driven Personalized Alignment
Humanizing LLMs: A Survey of Psychological Measurements with Tools, Datasets, and Human-Agent Applications