Glitch Tokens in Large Language Models: Categorization Taxonomy and Effective Detection

arXiv:2404.09894v1 Announce Type: new
Abstract: With the expanding application of Large Language Models (LLMs) in various domains, it becomes imperative to comprehensively investigate their unforeseen behaviors and consequent outcomes. In this study, we introduce and systematically explore the phenomenon of "glitch tokens", which are anomalous tokens produced by established tokenizers and could potentially compromise the models' quality of response. Specifically, we experiment on seven top popular LLMs utilizing three distinct tokenizers and involving a totally of 182,517 tokens. We present …

abstract application arxiv cs.cl cs.se detection domains explore glitch language language models large language large language models llms study taxonomy tokens type