Cover Image

CMD: a framework for Context-aware Model self-Detoxification

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Tang, Zecheng, Zhou, Keyan, Li, Juntao, Ding, Yuyang, Wang, Pinzheng, Yan, Bowen, Hua, Rejie, Zhang, Min
Format:	Preprint
Published:	2023
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Rethinking Negative Instances for Generative Named Entity Recognition
by: Ding, Yuyang, et al.
Published: (2024)

Revealing and Mitigating Over-Attention in Knowledge Editing
by: Wang, Pinzheng, et al.
Published: (2025)

L-CiteEval: Do Long-Context Models Truly Leverage Context for Responding?
by: Tang, Zecheng, et al.
Published: (2024)

LOOM-Scope: a comprehensive and efficient LOng-cOntext Model evaluation framework
by: Tang, Zecheng, et al.
Published: (2025)

OpenBA: An Open-sourced 15B Bilingual Asymmetric seq2seq Model Pre-trained from Scratch
by: Li, Juntao, et al.
Published: (2023)

Improving Rationality in the Reasoning Process of Language Models through Self-playing Game
by: Wang, Pinzheng, et al.
Published: (2025)

Revisiting Long-context Modeling from Context Denoising Perspective
by: Tang, Zecheng, et al.
Published: (2025)

MMLongCite: A Benchmark for Evaluating Fidelity of Long-Context Vision-Language Models
by: Zhou, Keyan, et al.
Published: (2025)

LongRM: Revealing and Unlocking the Context Boundary of Reward Modeling
by: Tang, Zecheng, et al.
Published: (2025)

MemReread: Enhancing Agentic Long-Context Reasoning via Memory-Guided Rereading
by: Ji, Baibei, et al.
Published: (2026)

MemLong: Memory-Augmented Retrieval for Long Text Modeling
by: Liu, Weijie, et al.
Published: (2024)

Revealing and Mitigating the Local Pattern Shortcuts of Mamba
by: You, Wangjie, et al.
Published: (2024)

LOGO -- Long cOntext aliGnment via efficient preference Optimization
by: Tang, Zecheng, et al.
Published: (2024)

OpenBA-V2: Reaching 77.3% High Compression Ratio with Fast Multi-Stage Pruning
by: Qiao, Dan, et al.
Published: (2024)

CoGenesis: A Framework Collaborating Large and Small Language Models for Secure Context-Aware Instruction Following
by: Zhang, Kaiyan, et al.
Published: (2024)

Towards DS-NER: Unveiling and Addressing Latent Noise in Distant Annotations
by: Ding, Yuyang, et al.
Published: (2025)

SCAN: Self-Denoising Monte Carlo Annotation for Robust Process Reward Learning
by: Ding, Yuyang, et al.
Published: (2025)

Efficient Reasoning for LLMs through Speculative Chain-of-Thought
by: Wang, Jikai, et al.
Published: (2025)

MemoryRewardBench: Benchmarking Reward Models for Long-Term Memory Management in Large Language Models
by: Tang, Zecheng, et al.
Published: (2026)

Adaptive Detoxification: Safeguarding General Capabilities of LLMs through Toxicity-Aware Knowledge Editing
by: Lu, Yifan, et al.
Published: (2025)

Where Matters More Than What: Decoding-aligned KV Cache Compression via Position-aware Pseudo Queries
by: Tian, Zhenxu, et al.
Published: (2026)

On the Robustness of Knowledge Editing for Detoxification
by: Dong, Ming, et al.
Published: (2026)

GPT-DETOX: An In-Context Learning-Based Paraphraser for Text Detoxification
by: Pesaranghader, Ali, et al.
Published: (2024)

Demonstration Augmentation for Zero-shot In-context Learning
by: Su, Yi, et al.
Published: (2024)

ylmmcl at Multilingual Text Detoxification 2025: Lexicon-Guided Detoxification and Classifier-Gated Rewriting
by: Lai-Lopez, Nicole, et al.
Published: (2025)

Unleashing LLM Reasoning Capability via Scalable Question Synthesis from Scratch
by: Ding, Yuyang, et al.
Published: (2024)

Living in the Moment: Can Large Language Models Grasp Co-Temporal Reasoning?
by: Su, Zhaochen, et al.
Published: (2024)

Query-focused and Memory-aware Reranker for Long Context Processing
by: Li, Yuqing, et al.
Published: (2026)

Elastic Attention: Test-time Adaptive Sparsity Ratios for Efficient Transformers
by: Tang, Zecheng, et al.
Published: (2026)

SciCUEval: A Comprehensive Dataset for Evaluating Scientific Context Understanding in Large Language Models
by: Yu, Jing, et al.
Published: (2025)

MemeCMD: An Automatically Generated Chinese Multi-turn Dialogue Dataset with Contextually Retrieved Memes
by: Wang, Yuheng, et al.
Published: (2025)

Learning-to-Context Slope: Evaluating In-Context Learning Effectiveness Beyond Performance Illusions
by: Wang, Dingzriui, et al.
Published: (2025)

Parameter-Efficient Detoxification with Contrastive Decoding
by: Niu, Tong, et al.
Published: (2024)

When Does Context Help? Error Dynamics of Contextual Information in Large Language Models
by: Wang, Dingzirui, et al.
Published: (2026)

DSCD: Large Language Model Detoxification with Self-Constrained Decoding
by: Dong, Ming, et al.
Published: (2025)

SciKnowEval: Evaluating Multi-level Scientific Knowledge of Large Language Models
by: Feng, Kehua, et al.
Published: (2024)

Detoxification for LLM: From Dataset Itself
by: Shao, Wei, et al.
Published: (2026)

Detoxification of Large Language Models through Output-layer Fusion with a Calibration Model
by: Tian, Yuanhe, et al.
Published: (2025)

Fine-Grained Detoxification via Instance-Level Prefixes for Large Language Models
by: Yi, Xin, et al.
Published: (2024)

The Power of Personality: A Human Simulation Perspective to Investigate Large Language Model Agents
by: Duan, Yifan, et al.
Published: (2025)