From the 1 of 6 linked papers with an AI index.
6 papers
PRISM Edit: One Vector for All Temporal Answers
Chen Huang, Qi Zheng, Ruiqin Zheng +2
The paper proposes PRISM Edit, a method that updates large language models to handle changing temporal facts by learning a single representation that can be modulated for different…
Illusions of Confidence? Diagnosing LLM Truthfulness via Neighborhood Consistency
Haoming Xu, Ningyuan Zhao, Yunzhi Yao +7
As Large Language Models (LLMs) are increasingly deployed in real-world settings, correctness alone is insufficient. Reliable deployment requires maintaining truthful beliefs under…
ChineseHarm-Bench: A Chinese Harmful Content Detection Benchmark
Kangwei Liu, Siyuan Cheng, Bozhong Tian +7
Large language models (LLMs) have been increasingly applied to automated harmful content detection tasks, assisting moderators in identifying policy violations and improving the ov…
Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training
Mengru Wang, Xingyu Chen, Yue Wang +12
Mixture-of-Experts (MoE) architectures within Large Reasoning Models (LRMs) have achieved impressive reasoning capabilities by selectively activating experts to facilitate structur…
Knowledge Mechanisms in Large Language Models: A Survey and Perspective
Mengru Wang, Yunzhi Yao, Ziwen Xu +10
Understanding knowledge mechanisms in Large Language Models (LLMs) is crucial for advancing towards trustworthy AGI. This paper reviews knowledge mechanism analysis from a novel ta…
Editing Conceptual Knowledge for Large Language Models
Xiaohan Wang, Shengyu Mao, Ningyu Zhang +6
Recently, there has been a growing interest in knowledge editing for Large Language Models (LLMs). Current approaches and evaluations merely explore the instance-level editing, whi…