Image de couverture de livre

On the Robustness of Knowledge Editing for Detoxification

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Dong, Ming, Tang, Shiyi, Peng, Ziyan, Chen, Guanyi, He, Tingting
Format:	Preprint
Publié:	2026
Sujets:	Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

DSCD: Large Language Model Detoxification with Self-Constrained Decoding
par: Dong, Ming, et autres
Publié: (2025)

How Much Do LLMs Know About Chinese Zero Pronouns?
par: Li, Yifei, et autres
Publié: (2026)

Adaptive Detoxification: Safeguarding General Capabilities of LLMs through Toxicity-Aware Knowledge Editing
par: Lu, Yifan, et autres
Publié: (2025)

CCNU at SemEval-2025 Task 3: Leveraging Internal and External Knowledge of Large Language Models for Multilingual Hallucination Annotation
par: Liu, Xu, et autres
Publié: (2025)

How Do People Quantify Naturally: Evidence from Mandarin Picture Description
par: Zhang, Yayun, et autres
Publié: (2026)

Do Large Language Models Judge Error Severity Like Humans?
par: Sun, Diege, et autres
Publié: (2025)

Emotional Supporters often Use Multiple Strategies in a Single Turn
par: Bai, Xin, et autres
Publié: (2025)

Rich Semantic Knowledge Enhanced Large Language Models for Few-shot Chinese Spell Checking
par: Dong, Ming, et autres
Publié: (2024)

When Seekers Are Hard to Help: Evaluating Emotional Support Dialogue Systems in Worst-Case Interactions
par: Yang, Jiajie, et autres
Publié: (2026)

An Effective, Robust and Fairness-aware Hate Speech Detection Framework
par: Mou, Guanyi, et autres
Publié: (2024)

Attribution Analysis Meets Model Editing: Advancing Knowledge Correction in Vision Language Models with VisEdit
par: Chen, Qizhou, et autres
Publié: (2024)

Mechanistic Circuit-Based Knowledge Editing in Large Language Models
par: Zhao, Tianyi, et autres
Publié: (2026)

LyapLock: Bounded Knowledge Preservation in Sequential Large Language Model Editing
par: Wang, Peng, et autres
Publié: (2025)

SetKE: Knowledge Editing for Knowledge Elements Overlap
par: Wei, Yifan, et autres
Publié: (2025)

CMD: a framework for Context-aware Model self-Detoxification
par: Tang, Zecheng, et autres
Publié: (2023)

Knowledge Editing through Chain-of-Thought
par: Wang, Changyue, et autres
Publié: (2024)

Context-Robust Knowledge Editing for Language Models
par: Park, Haewon, et autres
Publié: (2025)

Detoxification for LLM: From Dataset Itself
par: Shao, Wei, et autres
Publié: (2026)

Fine-Grained Detoxification via Instance-Level Prefixes for Large Language Models
par: Yi, Xin, et autres
Publié: (2024)

ylmmcl at Multilingual Text Detoxification 2025: Lexicon-Guided Detoxification and Classifier-Gated Rewriting
par: Lai-Lopez, Nicole, et autres
Publié: (2025)

DeepEdit: Knowledge Editing as Decoding with Constraints
par: Wang, Yiwei, et autres
Publié: (2024)

Editing the Mind of Giants: An In-Depth Exploration of Pitfalls of Knowledge Editing in Large Language Models
par: Hsueh, Cheng-Hsun, et autres
Publié: (2024)

Targeted Efficient Fine-tuning: Optimizing Parameter Updates with Data-Driven Sample Selection
par: Dong, Ming, et autres
Publié: (2024)

FISH-Tuning: Enhancing PEFT Methods with Fisher Information
par: Xue, Kang, et autres
Publié: (2025)

EvoEdit: Evolving Null-space Alignment for Robust and Efficient Knowledge Editing
par: Lyu, Sicheng, et autres
Publié: (2025)

Breaking Bad Tokens: Detoxification of LLMs Using Sparse Autoencoders
par: Goyal, Agam, et autres
Publié: (2025)

Text Detoxification as Style Transfer in English and Hindi
par: Mukherjee, Sourabrata, et autres
Publié: (2024)

Benchmarking and Rethinking Knowledge Editing for Large Language Models
par: He, Guoxiu, et autres
Publié: (2025)

Revealing the Deceptiveness of Knowledge Editing: A Mechanistic Analysis of Superficial Editing
par: Xie, Jiakuan, et autres
Publié: (2025)

Mitigating Heterogeneous Token Overfitting in LLM Knowledge Editing
par: Liu, Tianci, et autres
Publié: (2025)

Beyond Local Edits: Embedding-Virtualized Knowledge for Broader Evaluation and Preservation of Model Editing
par: Liu, Shuainan, et autres
Publié: (2026)

Event-level Knowledge Editing
par: Peng, Hao, et autres
Publié: (2024)

Knowledge Editing with Dynamic Knowledge Graphs for Multi-Hop Question Answering
par: Lu, Yifan, et autres
Publié: (2024)

Diagnosing Model Editing via Knowledge Spectrum
par: Pan, Tsung-Hsuan, et autres
Publié: (2025)

Parameter-Efficient Detoxification with Contrastive Decoding
par: Niu, Tong, et autres
Publié: (2024)

Lifelong Knowledge Editing for LLMs with Retrieval-Augmented Continuous Prompt Learning
par: Chen, Qizhou, et autres
Publié: (2024)

Intrinsic Task-based Evaluation for Referring Expression Generation
par: Chen, Guanyi, et autres
Publié: (2024)

Computational Modelling of Plurality and Definiteness in Chinese Noun Phrases
par: Liu, Yuqi, et autres
Publié: (2024)

Learning to Edit: Aligning LLMs with Knowledge Editing
par: Jiang, Yuxin, et autres
Publié: (2024)

An Information-Theoretic Framework for Robust Large Language Model Editing
par: Chen, Qizhou, et autres
Publié: (2025)