Cover Image

GlitchProber: Advancing Effective Detection and Mitigation of Glitch Tokens in Large Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhang, Zhibo, Bai, Wuxia, Li, Yuxi, Meng, Mark Huasong, Wang, Kailong, Shi, Ling, Li, Li, Wang, Jun, Wang, Haoyu
Format:	Preprint
Published:	2024
Subjects:	Computation and Language Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Glitch Tokens in Large Language Models: Categorization Taxonomy and Effective Detection
by: Li, Yuxi, et al.
Published: (2024)

Circumventing Safety Alignment in Large Language Models Through Embedding Space Toxicity Attenuation
by: Zhang, Zhibo, et al.
Published: (2025)

Model-Editing-Based Jailbreak against Safety-aligned Large Language Models
by: Li, Yuxi, et al.
Published: (2024)

GlitchMiner: Mining Glitch Tokens in Large Language Models via Gradient-based Discrete Optimization
by: Wu, Zihui, et al.
Published: (2024)

A Glitch in the Matrix? Locating and Detecting Language Model Grounding with Fakepedia
by: Monea, Giovanni, et al.
Published: (2023)

Detecting LLM Fact-conflicting Hallucinations Enhanced by Temporal-logic-based Reasoning
by: Li, Ningke, et al.
Published: (2025)

Grokking or Glitching? How Low-Precision Drives Slingshot Loss Spikes
by: Hanqing, Liu, et al.
Published: (2026)

Point of View--Political Glitches
by: Shaw, Robert
Published: (2004)

TempGlitch: Evaluating Vision-Language Models for Temporal Glitch Detection in Gameplay Videos
by: Yu, Yakun, et al.
Published: (2026)

Detecting Manipulated Contents Using Knowledge-Grounded Inference
by: Meng, Mark Huasong, et al.
Published: (2025)

Beyond Correctness: Exposing LLM-generated Logical Flaws in Reasoning via Multi-step Automated Theorem Proving
by: Zheng, Xinyi, et al.
Published: (2025)

Drowzee: Metamorphic Testing for Fact-Conflicting Hallucination Detection in Large Language Models
by: Li, Ningke, et al.
Published: (2024)

Exposing the Ghost in the Transformer: Abnormal Detection for Large Language Models via Hidden State Forensics
by: Zhou, Shide, et al.
Published: (2025)

Digger: Detecting Copyright Content Mis-usage in Large Language Model Training
by: Li, Haodong, et al.
Published: (2024)

Detection and Mitigation of Glitches in LISA Data: A Machine Learning Approach
by: Houba, Niklas, et al.
Published: (2024)

Evaluating and Mitigating Linguistic Discrimination in Large Language Models
by: Dong, Guoliang, et al.
Published: (2024)

GlitchBench: Can large multimodal models detect video game glitches?
by: Taesiri, Mohammad Reza, et al.
Published: (2023)

Continuous Embedding Attacks via Clipped Inputs in Jailbreaking Large Language Models
by: Xu, Zihao, et al.
Published: (2024)

Normal Distribution of Crab Pulsar Glitch Activity from a Glitch Cluster Perspective
by: Zhu, Pei-Xin, et al.
Published: (2025)

Detection and Mitigation of Hallucination in Large Reasoning Models: A Mechanistic Perspective
by: Sun, Zhongxiang, et al.
Published: (2025)

Embedding Poisoning: Bypassing Safety Alignment via Embedding Semantic Shift
by: Yuan, Shuai, et al.
Published: (2025)

Understanding the Effectiveness of Coverage Criteria for Large Language Models: A Special Angle from Jailbreak Attacks
by: Zhou, Shide, et al.
Published: (2024)

Desinformationen als journalistische Glitches
by: von Reischach, Niklas
Published: (2026)

Investigation into Pulsar Glitch Parameters
by: Marcel, Miracle Chibuzor
Published: (2024)

Using Deep Convolutional Neural Networks to Detect Rendered Glitches in Video Games
by: Ling, Carlos Garcia, et al.
Published: (2024)

Advancing Text Classification with Large Language Models and Neural Attention Mechanisms
by: Lyu, Ning, et al.
Published: (2025)

Exploring Superfluid Angular Momentum Reservoir Effect on Pulsar Glitches and Forecasting Next Glitches of the Crab Pulsar
by: Zhu, Pei-Xin, et al.
Published: (2026)

A Glitch Detection and Removal Method for Three‐Component Seismic Data From Mars Based On Deep Learning
by: Jiangjie Zhang, et al.
Published: (2025)

Beyond the Scope: Security Testing of Permission Management in Team Workspace
by: Wan, Liuhuo, et al.
Published: (2025)

Mitigating Gradient Inversion Risks in Language Models via Token Obfuscation
by: Feng, Xinguo, et al.
Published: (2026)

Semantic Glitch: Agency and Artistry in an Autonomous Pixel Cloud
by: Zhang, Qing, et al.
Published: (2025)

Glitches in Decision Tree Ensemble Models
by: Chandra, Satyankar, et al.
Published: (2025)

Glitching pulsars as gravitational wave sources
by: Haskell, Brynmor, et al.
Published: (2023)

Efficient Temporal Tokenization for Mobility Prediction with Large Language Models
by: He, Haoyu, et al.
Published: (2025)

Open-Ended Video Game Glitch Detection with Agentic Reasoning and Temporal Grounding
by: Zheng, Muyang, et al.
Published: (2026)

Mitigating Heterogeneous Token Overfitting in LLM Knowledge Editing
by: Liu, Tianci, et al.
Published: (2025)

A Causal Explainable Guardrails for Large Language Models
by: Chu, Zhixuan, et al.
Published: (2024)

Null Stream Based Third-generation-ready Glitch Mitigation for Gravitational Wave Measurements
by: Narola, Harsh, et al.
Published: (2024)

STShield: Single-Token Sentinel for Real-Time Jailbreak Detection in Large Language Models
by: Wang, Xunguang, et al.
Published: (2025)

Maximum Likelihood Detection of Instrumental Glitches in LISA TDI Data
by: Sauter, Orion, et al.
Published: (2025)