Decision Making
Decision-making research currently focuses on improving human-AI collaboration and developing more robust and explainable AI decision-making systems. Key areas include enhancing AI explanations to better align with human reasoning, incorporating uncertainty and context into AI models (e.g., using Bayesian methods, analogical reasoning, and hierarchical reinforcement learning), and evaluating AI decision-making performance against human benchmarks, often using novel metrics and frameworks. This work is significant for advancing both our understanding of human decision processes and for building more effective and trustworthy AI systems across diverse applications, from healthcare and finance to autonomous driving and infrastructure management.
Papers
Language Models are Alignable Decision-Makers: Dataset and Application to the Medical Triage Domain
Brian Hu, Bill Ray, Alice Leung, Amy Summerville, David Joy, Christopher Funk, Arslan Basharat
Decision-Making Behavior Evaluation Framework for LLMs under Uncertain Context
Jingru Jia, Zehua Yuan, Junhao Pan, Paul McNamara, Deming Chen
CoSLight: Co-optimizing Collaborator Selection and Decision-making to Enhance Traffic Signal Control
Jingqing Ruan, Ziyue Li, Hua Wei, Haoyuan Jiang, Jiaming Lu, Xuantang Xiong, Hangyu Mao, Rui Zhao
Position: Foundation Agents as the Paradigm Shift for Decision Making
Xiaoqian Liu, Xingzhou Lou, Jianbin Jiao, Junge Zhang
ABI Approach: Automatic Bias Identification in Decision-Making Under Risk based in an Ontology of Behavioral Economics
Eduardo da C. Ramos, Maria Luiza M. Campos, Fernanda Baião
GameVLM: A Decision-making Framework for Robotic Task Planning Based on Visual Language Models and Zero-sum Games
Aoran Mei, Jianhua Wang, Guo-Niu Zhu, Zhongxue Gan
HighwayLLM: Decision-Making and Navigation in Highway Driving with RL-Informed Language Model
Mustafa Yildirim, Barkin Dagda, Saber Fallah