AI Paper Atlas

Research map / Large language models / Language, safety and interpretability

GlitchMiner: Mining Glitch Tokens in Large Language Models via Gradient-based Discrete Optimization

Zihui Wu, Haichang Gao, Ping Wang, Shudong Zhang, Zhaoxiang Liu, Shiguo Lian

AAAI 2026 · Large language models › Language, safety and interpretability · approach: Data and hallucination detection · 6 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use GlitchMiner instead of Magikarp at budget 2000GlitchMiner · 10-LLM averageDetected@2000: 885.6 -> 980.1Improved
use GlitchMiner instead of Magikarp at budget 1000GlitchMiner · Llama-3.1-8B-InstructDetected@1000: 664 -> 568Hurt
use GlitchMiner instead of MagikarpGlitchMiner · Llama-2-7B-chat-hfDetected@2000: 186 -> 532Improved
add local search (restrict to embedding neighborhood) (ablation)GlitchMiner · 10 LLMsDetected@1000Improved
increase neighborhood size K (ablation)GlitchMiner · 10 LLMsDetected@1000Hurt
increase batch size B (ablation)GlitchMiner · 10 LLMsDetected@1000No clear effect
random initialization instead of min l2-norm token (ablation)GlitchMiner · 10 LLMsDetected@1000No clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy