Yuxi Li

Yuxi Li

Auto-generated profile, based on publicly available information

Yuxi Li

Huazhong University of Science and Technology

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
12 July 2024 in Proceedings of the ACM on Software Engineering
Verified
Journal Article
Open access
YLYuxi Li
Yuxi Li
YLYi Liu
Yi Liu
GDGelei Deng
Gelei Deng
YZYing Zhang
Ying Zhang
WSWenjia Song
Wenjia Song
HWHaoyu Wang
Haoyu Wang
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 categorizations of the identified glitch tokens and symptoms exhibited by LLMs when interacting with glitch tokens. Based on our observation that glitch tokens tend to cluster in the embedding space, we propose GlitchHunter , a novel iterative clustering-based technique, for efficient glitch token detection. The evaluation shows that our approach notably outperforms three baseline methods on eight open-source LLMs. To the best of our knowledge, we present the first comprehensive study on glitch tokens. Our new detection further provides valuable insights into mitigating tokenization-related errors in LLMs.

27 October 2024
Verified
Conference Paper
Open access
ZZZhibo Zhang
Zhibo Zhang
WBWuxia Bai
Wuxia Bai
YLYuxi Li
Yuxi Li
MMMark Huasong Meng
Mark Huasong Meng
Kailong WangKailong Wang
Kailong Wang
HWHaoyu Wang
Haoyu Wang
Large language models (LLMs) have achieved unprecedented success in the field of natural language processing. However, the black-box nature of their internal mechanisms has brought many concerns about their trustworthiness and interpretability. Recent research has discovered a class of abnormal tokens in the model's vocabulary space and named them "glitch tokens". Those tokens, once included in the input, may induce the model to produce incorrect, irrelevant, or even harmful results, drastically undermining the reliability and practicality of LLMs. In this work, we aim to enhance the understanding of glitch tokens and propose techniques for their detection and mitigation. We first reveal the characteristic features induced by glitch tokens on LLMs, which are evidenced by significant deviations in the distributions of attention patterns and dynamic information from intermediate model layers. Based on the insights, we develop GlitchProber, a tool for efficient glitch token detection and mitigation. GlitchProber utilizes small-scale sampling, principal component analysis for accelerated feature extraction, and a simple classifier for efficient vocabulary screening. Taking one step further, GlitchProber rectifies abnormal model intermediate layer values to mitigate the destructive effects of glitch tokens. Evaluated on five mainstream open-source LLMs, GlitchProber demonstrates higher efficiency, precision, and recall compared to existing approaches, with an average F1 score of 0.86 and an average repair rate of 50.06%. GlitchProber unveils a novel path to address the challenges posed by glitch tokens and inspires future research toward more robust and interpretable LLMs. Our code is available at https://github.com/LLM-Integrity-Guard/GlitchProber.

4 August 2026
Verified
Book Chapter
Closed access
PDF file
JLJiaqing Li
Jiaqing Li
ZZZhibo Zhang
Zhibo Zhang
SZShide Zhou
Shide Zhou
YLYuxi Li
Yuxi Li
TYTianlong Yu
Tianlong Yu
Kailong WangKailong Wang
Kailong Wang

4 August 2026
Verified
Book Chapter
Closed access
PDF file
YLYuxi Li
Yuxi Li
YLYi Liu
Yi Liu
Yuekang LiYuekang Li
Yuekang Li
LSLing Shi
Ling Shi
GDGelei Deng
Gelei Deng
Kailong WangKailong Wang
Kailong Wang