GlitchMiner: Mining Glitch Tokens in Large Language Models via Gradient-based Discrete Optimization (2410.15052v4)

Abstract: Glitch tokens in LLMs can trigger unpredictable behaviors, threatening model reliability and safety. Existing detection methods rely on predefined patterns, limiting their adaptability across diverse LLM architectures. We propose GlitchMiner, a gradient-based discrete optimization framework that efficiently identifies glitch tokens by introducing entropy as a measure of prediction uncertainty and employing a local search strategy to explore the token space. Experiments across multiple LLM architectures demonstrate that GlitchMiner outperforms existing methods in detection accuracy and adaptability, achieving over 10% average efficiency improvement. This method enhances vulnerability assessment in LLMs, contributing to the development of more robust and reliable applications. Code is available at https://github.com/wooozihui/GlitchMiner.