Cover Image

GloSS over Toxicity: Understanding and Mitigating Toxicity in LLMs via Global Toxic Subspace

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Duan, Zenghao, Yin, Zhiyi, Shi, Zhichao, Pang, Liang, Jing, Shaoling, Wu, Jiayi, Yan, Yu, Shen, Huawei, Cheng, Xueqi
Format:	Preprint
Published:	2025
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

Projecting Out the Malice: A Global Subspace Approach to LLM Detoxification
by: Duan, Zenghao, et al.
Published: (2026)

Related Knowledge Perturbation Matters: Rethinking Multiple Pieces of Knowledge Editing in Same-Subject
by: Duan, Zenghao, et al.
Published: (2025)

from Benign import Toxic: Jailbreaking the Language Model via Adversarial Metaphors
by: Yan, Yu, et al.
Published: (2025)

LLM4MEA: Data-free Model Extraction Attacks on Sequential Recommenders via Large Language Models
by: Zhao, Shilong, et al.
Published: (2025)

Rowen: Adaptive Retrieval-Augmented Generation for Hallucination Mitigation in LLMs
by: Ding, Hanxing, et al.
Published: (2024)

Circular Reasoning: Understanding Self-Reinforcing Loops in Large Reasoning Models
by: Duan, Zenghao, et al.
Published: (2026)

Large Language Model Sourcing: A Survey
by: Pang, Liang, et al.
Published: (2025)

Do LLMs Play Dice? Exploring Probability Distribution Sampling in Large Language Models for Behavioral Simulation
by: Gu, Jia, et al.
Published: (2024)

HalluciDoctor: Mitigating Hallucinatory Toxicity in Visual Instruction Data
by: Yu, Qifan, et al.
Published: (2023)

Breaking the Cloak! Unveiling Chinese Cloaked Toxicity with Homophone Graph and Toxic Lexicon
by: Ma, Xuchen, et al.
Published: (2025)

ToxicTone: A Mandarin Audio Dataset Annotated for Toxicity and Toxic Utterance Tonality
by: Luo, Yu-Xiang, et al.
Published: (2025)

FrenchToxicityPrompts: a Large Benchmark for Evaluating and Mitigating Toxicity in French Texts
by: Brun, Caroline, et al.
Published: (2024)

Can LLMs Recognize Toxicity? A Structured Investigation Framework and Toxicity Metric
by: Koh, Hyukhun, et al.
Published: (2024)

Mitigating Text Toxicity with Counterfactual Generation
by: Bhan, Milan, et al.
Published: (2024)

Toxics
Published: (2014)

Do Prompts Guarantee Safety? Mitigating Toxicity from LLM Generations through Subspace Intervention
by: Singh, Himanshu, et al.
Published: (2026)

The Landscape of Toxicity: An Empirical Investigation of Toxicity on GitHub
by: Sarker, Jaydeb, et al.
Published: (2025)

LLM Latent Reasoning as Chain of Superposition
by: Deng, Jingcheng, et al.
Published: (2025)

SkillAttack: Automated Red Teaming of Agent Skills through Attack Path Refinement
by: Duan, Zenghao, et al.
Published: (2026)

The Evolution of Thought: Tracking LLM Overthinking via Reasoning Dynamics Analysis
by: Wei, Zihao, et al.
Published: (2025)

A Theory for Token-Level Harmonization in Retrieval-Augmented Generation
by: Xu, Shicheng, et al.
Published: (2024)

Improving Video Corpus Moment Retrieval with Partial Relevance Enhancement
by: Hou, Danyang, et al.
Published: (2024)

D-Models and E-Models: Diversity-Stability Trade-offs in the Sampling Behavior of Large Language Models
by: Gu, Jia, et al.
Published: (2026)

Enhancing Training Data Attribution for Large Language Models with Fitting Error Consideration
by: Wu, Kangxi, et al.
Published: (2024)

Think Before You Speak: Cultivating Communication Skills of Large Language Models via Inner Monologue
by: Zhou, Junkai, et al.
Published: (2023)

Event-aware Video Corpus Moment Retrieval
by: Hou, Danyang, et al.
Published: (2024)

Toxic Timescapes
Published: (2024)

Toxic truths
Published: (2020)

Toxic Parliaments
by: Sawer, Marian, et al.
Published: (2024)

Toxic Chemicals
by: Higgins, Thomas E., et al.
Published: (2020)

Toxic Heritage
Published: (2023)

Beyond Toxic: Toxicity Detection Datasets are Not Enough for Brand Safety
by: Korotkova, Elizaveta, et al.
Published: (2023)

Toxicity Begets Toxicity: Unraveling Conversational Chains in Political Podcasts
by: Rizwan, Naquee, et al.
Published: (2025)

Toxic Bias: Perspective API Misreads German as More Toxic
by: Nogara, Gianluca, et al.
Published: (2023)

Argument-Based Consistency in Toxicity Explanations of LLMs
by: Mothilal, Ramaravind Kommiya, et al.
Published: (2025)

Preference Tuning For Toxicity Mitigation Generalizes Across Languages
by: Li, Xiaochen, et al.
Published: (2024)

Inference-Time Toxicity Mitigation in Protein Language Models
by: Burda, Manuel Fernández, et al.
Published: (2026)

Chinese Toxic Language Mitigation via Sentiment Polarity Consistent Rewrites
by: Wang, Xintong, et al.
Published: (2025)

Cross-Model Comparative Loss for Enhancing Neuronal Utility in Language Understanding
by: Zhu, Yunchang, et al.
Published: (2023)

The Expanding Spectrum of Fuel Toxicity: A Migration‐Related Toxic Syndrome
by: Antonio Corsello, et al.
Published: (2026)