3 papers
cs.CL2025
Building Task Bots with Self-learning for Enhanced Adaptability, Extensibility, and Factuality
Xiaoying Zhang
Developing adaptable, extensible, and accurate task bots with minimal or zero human intervention is a significant challenge in dialog research. This thesis examines the obstacles a…
cs.CL2024
Self-Tuning: Instructing LLMs to Effectively Acquire New Knowledge through Self-Teaching
Xiaoying Zhang, Baolin Peng, Ye Tian +4
Large language models (LLMs) often struggle to provide up-to-date information due to their one-time training and the constantly evolving nature of the world. To keep LLMs current,…
cs.CL2024
Self-Alignment for Factuality: Mitigating Hallucinations in LLMs via Self-Evaluation
Xiaoying Zhang, Baolin Peng, Ye Tian +5
Despite showing increasingly human-like abilities, large language models (LLMs) often struggle with factual inaccuracies, i.e. "hallucinations", even when they hold relevant knowle…