KnowledgeVIS: Interpreting Language Models by Comparing Fill-in-the-Blank Prompts

arXiv:2403.04758v1 Announce Type: cross
Abstract: Recent growth in the popularity of large language models has led to their increased usage for summarizing, predicting, and generating text, making it vital to help researchers and engineers understand how and why they work. We present KnowledgeVis, a human-in-the-loop visual analytics system for interpreting language models using fill-in-the-blank sentences as prompts. By comparing predictions between sentences, KnowledgeVis reveals learned associations that intuitively connect what language models learn during training to natural language tasks downstream, …

abstract analytics arxiv cs.ai cs.cy cs.hc cs.lg engineers growth human language language models large language large language models loop making prompts researchers summarizing text type usage visual visual analytics vital work