Knowledge Circuits in Pretrained Transformers

The remarkable capabilities of modern large language models are rooted in their vast repositories of knowledge encoded within their parameters, enabling them to perceive the world and engage in reasoning. The inner workings of how these models store knowledge have long been a subject of intense interest and investigation among researchers. To date, most studies have concentrated on isolated components within these models, such as the Multilayer Perceptrons and attention head. In this paper, we delve into the computation graph of the language model to uncover the knowledge circuits that are instrumental in articulating specific knowledge. The experiments, conducted with GPT2 and TinyLLAMA, has allowed us to observe how certain information heads, relation heads, and Multilayer Perceptrons collaboratively encode knowledge within the model. Moreover, we evaluate the impact of current knowledge editing techniques on these knowledge circuits, providing deeper insights into the functioning and constraints of these editing methodologies. Finally, we utilize knowledge circuits to analyze and interpret language model behaviors such as hallucinations and in-context learning. We believe the knowledge circuit holds potential for advancing our understanding of Transformers and guiding the improved design of knowledge editing.

Authors

• Yunzhi Yao
• Ningyu Zhang Zhejiang University Zhejiang University - Ant Group Joint Laboratory of Knowledge Graph
• Zekun Xi
• Mengru Wang
• Ziwen Xu
• Shumin Deng NUS-NCS Joint Lab, National University of Singapore
• Huajun Chen College of Computer Science and Technology, Zhejiang University ZJU-Ant Group Joint Lab of Knowledge Graph Zhejiang Key Laboratory of Big Data Intelligent Computing

Keywords

No keywords are indexed for this paper.