Human Like
Research on "human-like" qualities in artificial intelligence focuses on developing models that exhibit behaviors and cognitive abilities resembling those of humans, aiming to improve AI's interaction with and understanding of humans. Current research emphasizes evaluating and enhancing aspects like reasoning, language understanding, and emotional intelligence in large language models (LLMs) and other AI architectures, often employing techniques like cognitive prompting, psychometric analysis, and imitation learning. This work is significant for advancing AI safety and trustworthiness, improving human-computer interaction, and providing novel tools for psychological and cognitive science research.
Papers
Is Cognition and Action Consistent or Not: Investigating Large Language Model's Personality
Yiming Ai, Zhiwei He, Ziyin Zhang, Wenhong Zhu, Hongkun Hao, Kai Yu, Lingjun Chen, Rui Wang
Kinematically Constrained Human-like Bimanual Robot-to-Human Handovers
Yasemin Göksu, Antonio De Almeida Correia, Vignesh Prasad, Alap Kshirsagar, Dorothea Koert, Jan Peters, Georgia Chalvatzaki
Driving Generative Agents With Their Personality
Lawrence J. Klinkert, Stephanie Buongiorno, Corey Clark
Generating Realistic Arm Movements in Reinforcement Learning: A Quantitative Comparison of Reward Terms and Task Requirements
Jhon Charaja, Isabell Wochner, Pierre Schumacher, Winfried Ilg, Martin Giese, Christophe Maufroy, Andreas Bulling, Syn Schmitt, Daniel F. B. Haeufle