2024/10/19 by Zihui Wu, Wu, Zihui, Haichang Gao +9 · 1 citation
Computer Science · #Artificial Intelligence (cs.AI) #Data Mining Algorithms and Applications #FOS: Computer and information sciences #Natural Language Processing Techniques #Topic Modeling
paper · pdf · doi:10.48550/arxiv.2410.15052
openalex publication_date 2024/10/19 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Glitch tokens, inputs that trigger unpredictable or anomalous behavior in Large Language Models (LLMs), pose significant challenges to model reliability and safety. Existing detection methods primarily rely on heuristic embedding patterns or statistical anomalies within internal representations, limiting their generalizability across different model architectures and potentially missing anomalies that deviate from observed patterns. We introduce GlitchMiner, an behavior-driven framework designed to identify glitch tokens by maximizing predictive entropy. Leveraging a gradient-guided local search strategy, GlitchMiner efficiently explores the discrete token space without relying on model-specific heuristics or large-batch sampling. Extensive experiments across ten LLMs from five major model families demonstrate that GlitchMiner consistently outperforms existing approaches in detection accuracy and query efficiency, providing a generalizable and scalable solution for effective glitch token discovery. Code is available at [https://github.com/wooozihu/GlitchMiner]