Results 101 to 110 of about 89,825 (246)

Exploring Qualitative Research Using LLMs [PDF]

, 2023
The advent of AI driven large language models (LLMs) have stirred discussions about their role in qualitative research. Some view these as tools to enrich human understanding, while others perceive them as threats to the core values of the discipline ...
Bano, Muneera, Zowghi, Didar, Whittle, Jon   +2 more
core  

Towards a Compositional Framework for Describing Human Phenotypes

Advanced Science, EarlyView.
The Phenotype Assembly Method (PhenoAM) decomposes phenotype variables into measurable Features and typed Qualifiers, enabling standardized, machine‐readable Phenome Data Elements (PhenoDEs) that preserve measurement context. Applied in the International Human Phenome Project (IHPP), the framework yields 58 371 PhenoDEs and supports component‐level ...
Wanting Hu, Yunchao Ling, Xinyue Hu, Wei Chen, Rong Zhou, Xinhao Zhuang, Yanfeng Jiang, Jialu Zhao, Xingdong Chen, Jingchun Luo, Li Jin, Guoqing Zhang   +11 more
wiley   +1 more source

Digital Friends and Empathy Blindness

Open Philosophy
Can chatbot-based virtual relationships replace physical ones? One possible bottleneck is lack of empathy in chatbots, as well as the attraction of physical relationships.
Bangsgaard Alberte Romme, Kløve Ryelund Cecilia, Lind Nilsson Mathilde Marie, Søgaard Anders   +3 more
doaj   +1 more source

Programming Assessment in E-Learning through Rule-Based Automatic Question Generation with Large Language Models

Journal of Applied Informatics and Computing
This study develops an evaluation instrument for Python programming using a Rule-Based Automatic Question Generation (AQG) system integrated with Large Language Models (LLMs), designed based on the Revised Bloom’s Taxonomy.
Halim Teguh Saputro, Usman Nurhasan, Vivi Nur Wijayaningrum   +2 more
doaj   +1 more source

MAPA: A Semantic Network Framework for Functional Module Discovery and Interpretation in Multi‐Omics Data

Advanced Science, EarlyView.
MAPA transforms complex multi‐omics data into biologically coherent functional modules by integrating pathway information with molecular interaction networks. Retrieval‐augmented large language models then generate structured, literature‐informed interpretations.
Yifei Ge, Feifan Zhang, Yijiang Liu, Chao Jiang, Peng Gao, Nguan Soon Tan, Sai Zhang, Yuchen Shen, Qianyi Zhou, Xin Zhou, Xiao Wang, Fangqing Zhao, Chuchu Wang, Xiaotao Shen   +13 more
wiley   +1 more source

ChatGPT Relies More Heavily on Consonants Than on Vowels to Recognize Words

Journal of Cognition
Humans develop biases during language learning. For example, we rely more heavily on consonants than on vowels to identify words. Advances on artificial intelligence have allowed the development of proficient large language models that sometimes mimic ...
Juan Manuel Toro
doaj   +1 more source

LLMs for Cyber Security: New Opportunities [PDF]

Large language models (LLMs) are a class of powerful and versatile models that are beneficial to many industries. With the emergence of LLMs, we take a fresh look at cyber security, specifically exploring and summarizing the potential of LLMs in ...
Divakaran, Dinil Mon, Peddinti, Sai Teja
core  

Knowledge Internalized in LLMs

LLMs, trained on a diverse range of resources, internalize a substantial amount of knowledge. Understanding this internalized knowledge is crucial for assessing the accuracy and reliability of their outputs, guiding improvements in model design, and ...
Tang, Nan, Sun, Kai, Sun, Yushi, Yang, Xiao   +3 more
core   +1 more source

LLMs as Representation Generators for Gradient‐Free Scientific Optimization: A Case Study in Battery Fast Charging

Advanced Science, EarlyView.
Large language models serve as representation generators for gradient‐free scientific optimization. Two complementary approaches produce executable battery‐charging policies either directly or through LLM‐designed neural representations coupled to Bayesian optimization.
Ge Lei, Ferran Brosa Planella, Sterling G. Baird, Samuel J. Cooper   +3 more
wiley   +1 more source

A Generalizable Multimodal Model for Treatment‐Stratified Risk and Survival Assessment under Real‐World Constraints: A Multi‐Center Study of Colorectal Cancer

Advanced Science, EarlyView.
DAIMS is a multimodal model for treatment stratified risk and survival assessment in colorectal cancer. Training draws on pathology, genomics, and clinical reports, yet inference requires only whole slide images, and adaptation to new cohorts proceeds without target survival outcomes.
Chuangjie Cao, Zheyi Ji, Chang He, Jiying Wang, Xiaoming Luo, Junyi Liu, Xiaohu Jing, Fang Yan, Yirong Chen, Linhao Qu, Sen Yang, Le Lu, Yuming Jiang, Xiyue Wang, Chengyun Dou, Junhan Zhao   +15 more
wiley   +1 more source