DCU Insight AQ
DCU Insight AQ is not a defined scientific topic or project readily identifiable in the provided abstracts. The abstracts cover a broad range of research using Large Language Models (LLMs) and other machine learning techniques across diverse fields, including legal reasoning, medical diagnosis, materials science, and anomaly detection. Current research focuses on improving LLM performance through techniques like multi-agent frameworks, multimodal data integration, and careful data curation, as well as addressing challenges such as hallucinations, bias, and efficient model training. These advancements have the potential to significantly improve data analysis, automate complex tasks, and enhance decision-making across numerous scientific and industrial domains.
Papers
Insights into Classifying and Mitigating LLMs' Hallucinations
Alessandro Bruno, Pier Luigi Mazzeo, Aladine Chetouani, Marouane Tliba, Mohamed Amine Kerkouri
A Comparative Analysis of the COVID-19 Infodemic in English and Chinese: Insights from Social Media Textual Data
Jia Luo, Daiyun Peng, Lei Shi, Didier El Baz, Xinran Liu
Deep Phenotyping of Non-Alcoholic Fatty Liver Disease Patients with Genetic Factors for Insights into the Complex Disease
Tahmina Sultana Priya, Fan Leng, Anthony C. Luehrs, Eric W. Klee, Alina M. Allen, Konstantinos N. Lazaridis, Danfeng, Yao, Shulan Tian
Assessing Logical Puzzle Solving in Large Language Models: Insights from a Minesweeper Case Study
Yinghao Li, Haorui Wang, Chao Zhang
Simulation-based Inference for Exoplanet Atmospheric Retrieval: Insights from winning the Ariel Data Challenge 2023 using Normalizing Flows
Mayeul Aubin, Carolina Cuesta-Lazaro, Ethan Tregidga, Javier Viaña, Cecilia Garraffo, Iouli E. Gordon, Mercedes López-Morales, Robert J. Hargreaves, Vladimir Yu. Makhnev, Jeremy J. Drake, Douglas P. Finkbeiner, Phillip Cargile
High-dimensional manifold of solutions in neural networks: insights from statistical physics
Enrico M. Malatesta