Department of Psychology, National Chengchi University
114-1 Academic Seminar
Speaker: Associate Research Fellow Hannah Hsuan Huang (Institute of Information Science, Academia Sinica)
Title: The Recent Advances of LLMs
Date & Time: December 11, 2025 (Thursday), 14:10–16:00
Venue: Psychology Department Conference Room 080101, Kwoh-Fu Building, National Chengchi University
All faculty and students are cordially invited to attend.
This talk provides an overview of the rapid progress, learning paradigms, and fundamental advantages of Large Language Models (LLMs). It discusses advanced reasoning techniques such as Chain-of-Thought (CoT) and Reasoning LLMs for improving logical inference, as well as Retrieval-Augmented Generation (RAG) and the proposed Cache-Augmented Generation (CAG) as solutions to limitations in knowledge access, recency, and generation latency. Furthermore, the presentation explores the current research landscape, focusing on model efficiency, strategies for mitigating LLM biases, safety alignment, and the development of next-generation multimodal systems.
Dr. Huang received her Ph.D. from the Department of Computer Science and Information Engineering at National Taiwan University. She previously served as an Assistant Professor in the Department of Computer Science at National Chengchi University and is currently an Associate Research Fellow at the Institute of Information Science, Academia Sinica.
Her research integrates artificial intelligence and language technologies, with a focus on computational modeling of metaphor comprehension and the interaction between linguistic understanding and human knowledge representation. She has pioneered new directions in Chinese discourse analysis.
Dr. Huang’s research has been widely published in top-tier journals and international conferences in artificial intelligence, natural language processing, and information retrieval. She has also served multiple times as co-chair and program committee member for international conferences such as SIGIR and ROCLING, contributing significantly to the advancement of interdisciplinary research in language and AI.
https://homepage.iis.sinica.edu.tw/pages/hhhuang/index_zh.html
