Decision Logic

Decision logic research focuses on understanding and improving how artificial systems make choices, aiming for both accuracy and explainability. Current efforts concentrate on enhancing large language models (LLMs) for decision-making, often integrating them with other models like 3D scene perception systems for autonomous driving or using constraint programming for robot behavior planning. These advancements are crucial for building trustworthy and reliable AI systems across various applications, from autonomous vehicles to robotics, by improving decision-making performance and providing insights into the reasoning process.

Papers

October 6, 2024

Alignment Between the Decision-Making Logic of LLMs and Human Cognition: A Case Study on Legal LLMs
Lu Chen, Yuxuan Huang, Yixing Li, Yaohui Jin, Shuai Zhao, Zilong Zheng, Quanshi Zhang
Large Language Model Case Study Human Cognition Logical Inference Decision Logic

August 25, 2024

Making Large Language Models Better Planners with Reasoning-Decision Alignment
Zhijian Huang, Tao Tang, Shaoxiang Chen, Sihao Lin, Zequn Jie, Lin Ma, Guangrun Wang, Xiaodan Liang
Large Language Model Autonomous Driving AI Reasoning Autonomous Driving Method Decision Logic

February 24, 2024

Foot In The Door: Understanding Large Language Model Jailbreaking via Cognitive Psychology
Zhenhua Wang, Wei Xie, Baosheng Wang, Enze Wang, Zhiwen Gui, Shuoyoucheng Ma, Kai Chen
Large Language Model Jailbreak Attack Human Decision Cognitive Approach Cognitive Psychology Decision Logic

January 8, 2024

DME-Driver: Integrating Human Decision Logic and 3D Scene Perception in Autonomous Driving
Wencheng Han, Dongqian Guo, Cheng-Zhong Xu, Jianbing Shen
Autonomous Driving Self Driving Car Autonomous Driving System Decision Logic 3d Scene Perception Perception Aware Planning

October 3, 2023

Safe and Robust Robot Behavior Planning via Constraint Programming
Jan Vermaelen, Tom Holvoet
Autonomous System Safety Constraint Constraint Programming Model Checking Robust Motion Planning Decision Logic

July 13, 2023

Probabilistic Constrained Reinforcement Learning with Formal Interpretability
Yanran Wang, Qiuchen Qian, David Boyle
Reinforcement Learning Policy OpTimization Constrained Reinforcement Learning Sequential Decision Making Problem Wasserstein Gradient Built in Interpretability Decision Logic

June 23, 2023

Co-creating a globally interpretable model with human input
Rahul Nair
Interpretable Model Human Ai Collaboration Natural Language Input Decision Logic Boolean Rule Joint Decision Making

October 13, 2022

Self-explaining deep models with logic rule reasoning
Seungeon Lee, Xiting Wang, Sungwon Han, Xiaoyuan Yi, Xing Xie, Meeyoung Cha
Deep Model Predictive Performance Logical Rule Explanation Capability Decision Logic

March 24, 2022

NPC: Neuron Path Coverage via Characterizing Decision Logic of Deep Neural Networks
Xiaofei Xie, Tianlin Li, Jian Wang, Lei Ma, Qing Guo, Felix Juefei-Xu, Yang Liu
Deep Neural Network Coverage Criterion Neuron Coverage Decision Logic DNN Testing Social NPC

March 6, 2022

Diversifying Agent's Behaviors in Interactive Decision Models
Yinghui Pan, Hanyi Zhang, Yifeng Zeng, Biyang Ma, Jing Tang, Zhong Ming
Multiple Agent Behavior Style Top K Diverse Agent Behavioral Feature Decision Logic