4 papers
Shuttle Between the Instructions and the Parameters of Large Language Models
Wangtao Sun, Haotian Xu, Huanxuan Liao +5
The interaction with Large Language Models (LLMs) through instructions has been extensively investigated in the research community. While instructions have been widely used as the…
Beyond Instruction Following: Evaluating Inferential Rule Following of Large Language Models
Wangtao Sun, Chenxiang Zhang, XueYou Zhang +7
Although Large Language Models (LLMs) have demonstrated strong ability, they are further supposed to be controlled and guided by in real-world scenarios to be safe, accurate, and i…
ONSEP: A Novel Online Neural-Symbolic Framework for Event Prediction Based on Large Language Model
Xuanqing Yu, Wangtao Sun, Jingwei Li +3
In the realm of event prediction, temporal knowledge graph forecasting (TKGF) stands as a pivotal technique. Previous approaches face the challenges of not utilizing experience dur…
ExpNote: Black-box Large Language Models are Better Task Solvers with Experience Notebook
Wangtao Sun, Xuanqing Yu, Shizhu He +2
Black-box Large Language Models (LLMs) have shown great power in solving various tasks and are considered general problem solvers. However, LLMs still fail in many specific tasks a…