It is the subfield of computer science that focuses on creating systems capable of intelligent behavior, including problem solving, learning, adaptation, perception, and language understanding.
The article by Rita Stampfl, Igor Ivki, and Barbara Geyer discusses the implementation of Large Language Models (LLMs), particularly ChatGPT, in role-playing simulation games to promote active learning. The authors…
Continue readingThe paper evaluates the rationality and cognitive biases of seven Large Language Models (LLMs) using tasks from cognitive psychology. The LLMs display irrationality in these tasks, often providing incorrect answers…
Continue readingThe article discusses the lack of effective user participation in current language model-driven agents due to the vagueness commonly found in user instructions. To address this, the authors introduce Intention-in-Interaction…
Continue readingThe article by Ruqing Xu discusses the design of an algorithm that aids in decision making. It contemplates whether to act directly based on the algorithm’s prediction or delegate the…
Continue readingThe study by Zijian Ding and Joel Chan from the University of Maryland introduces an ‘intelligent canvas’ – a new approach to visual data analysis. This canvas integrates generative AI…
Continue readingGhostWriter is an AI-powered environment that personalizes the writing process. It uses large language models (LLMs) to learn the user’s writing style as they write, while also allowing for explicit…
Continue readingThe article presents a visualization approach to explore the statuses and behaviors of agents within Large Language Model-based Autonomous Systems (LLMAS). A pipeline is proposed that forms a behavior structure…
Continue readingThe article discusses the role of large language models (LLMs) in chemistry, focusing on tasks such as drug discovery and material science. Despite the remarkable capabilities of LLMs in natural…
Continue readingThe paper introduces VisLingInstruct, an innovative method to improve Multi-Modal Language Models (MMLMs) in zero-shot learning tasks. Current MMLMs’ performance relies heavily on the quality of instructions, and VisLingInstruct addresses…
Continue readingThe paper presents a new innovative approach to Multiple-criteria Decision Analysis (MCDA) in cybersecurity by integrating the Analytic Hierarchy Process (AHP) and Generative Pre-trained Transformer 4 (GPT-4). The study focuses…
Continue readingLooks like you're using an ad blocker. Please support us by disabling these ad blocker.
