Exploratory Study
Exploratory studies in various scientific fields currently leverage large language models (LLMs) and other machine learning techniques to investigate diverse research questions. These studies focus on areas such as improving data analysis workflows, evaluating the reliability and biases of LLMs in different applications (e.g., grading, information retrieval), and assessing the impact of data quality on AI-assisted tools. This research is significant because it helps refine existing AI methods, identify and mitigate biases, and ultimately improve the trustworthiness and usability of AI systems across a range of practical applications.
Papers
Enhancing Supply Chain Visibility with Generative AI: An Exploratory Case Study on Relationship Prediction in Knowledge Graphs
Ge Zheng, Alexandra Brintrup
Chatting with Logs: An exploratory study on Finetuning LLMs for LogQL
Vishwanath Seshagiri, Siddharth Balyan, Vaastav Anand, Kaustubh Dhole, Ishan Sharma, Avani Wildani, José Cambronero, Andreas Züfle
Typologie des comportements utilisateurs : {é}tude exploratoire des sessions de recherche complexe sur le Web
Claire Ibarboure (CLLE), Ludovic Tanguy (CLLE), Franck Amadieu (CLLE)