Imagen de Portada

CATNIP: LLM Unlearning via Calibrated and Tokenized Negative Preference Alignment

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Yang, Zhengbang, Zhong, Yisheng, Hong, Junyuan, Zhu, Zhuangdi
Formato:	Preprint
Publicado:	2026
Materias:	Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Hierarchical Federated Unlearning for Large Language Models
por: Zhong, Yisheng, et al.
Publicado: (2025)

DUET: Distilled LLM Unlearning from an Efficiently Contextualized Teacher
por: Zhong, Yisheng, et al.
Publicado: (2026)

ChatWise: A Strategy-Guided Chatbot for Enhancing Cognitive Support in Older Adults
por: Yang, Zhengbang, et al.
Publicado: (2025)

Distribution Corrected Offline Data Distillation for Large Language Models
por: Zhang, Yumeng, et al.
Publicado: (2026)

Harmonizing Multi-Objective LLM Unlearning via Unified Domain Representation and Bidirectional Logit Distillation
por: Zhong, Yisheng, et al.
Publicado: (2026)

Sports Intelligence: Assessing the Sports Understanding Capabilities of Language Models through Question Answering from Text to Video
por: Yang, Zhengbang, et al.
Publicado: (2024)

Simplicity Prevails: Rethinking Negative Preference Optimization for LLM Unlearning
por: Fan, Chongyu, et al.
Publicado: (2024)

Align-then-Unlearn: Embedding Alignment for LLM Unlearning
por: Spohn, Philipp, et al.
Publicado: (2025)

Language and Multimodal Models in Sports: A Survey of Datasets and Applications
por: Xia, Haotian, et al.
Publicado: (2024)

DRAGON: Guard LLM Unlearning in Context via Negative Detection and Reasoning
por: Wang, Yaxuan, et al.
Publicado: (2025)

LUNE: Efficient LLM Unlearning via LoRA Fine-Tuning with Negative Examples
por: Liu, Yezi, et al.
Publicado: (2025)

Panacea: Pareto Alignment via Preference Adaptation for LLMs
por: Zhong, Yifan, et al.
Publicado: (2024)

Negative Preference Optimization: From Catastrophic Collapse to Effective Unlearning
por: Zhang, Ruiqi, et al.
Publicado: (2024)

Bridging the Gap Between Preference Alignment and Machine Unlearning
por: Feng, Xiaohua, et al.
Publicado: (2025)

Cal-DPO: Calibrated Direct Preference Optimization for Language Model Alignment
por: Xiao, Teng, et al.
Publicado: (2024)

Less is More: Improving LLM Alignment via Preference Data Selection
por: Deng, Xun, et al.
Publicado: (2025)

As Simple as Fine-tuning: LLM Alignment via Bidirectional Negative Feedback Loss
por: Mao, Xin, et al.
Publicado: (2024)

SEAL: Steerable Reasoning Calibration of Large Language Models for Free
por: Chen, Runjin, et al.
Publicado: (2025)

CTPD: Cross Tokenizer Preference Distillation
por: Nguyen, Truong, et al.
Publicado: (2026)

SparsePO: Controlling Preference Alignment of LLMs via Sparse Token Masks
por: Christopoulou, Fenia, et al.
Publicado: (2024)

Safety Alignment via Constrained Knowledge Unlearning
por: Shi, Zesheng, et al.
Publicado: (2025)

OpenUnlearning: Accelerating LLM Unlearning via Unified Benchmarking of Methods and Metrics
por: Dorna, Vineeth, et al.
Publicado: (2025)

Unlearning What Matters: Token-Level Attribution for Precise Language Model Unlearning
por: Wu, Jiawei, et al.
Publicado: (2026)

PMMT: Preference Alignment in Multilingual Machine Translation via LLM Distillation
por: Sun, Shuqiao, et al.
Publicado: (2024)

PMoL: Parameter Efficient MoE for Preference Mixing of LLM Alignment
por: Liu, Dongxu, et al.
Publicado: (2024)

GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection
por: Deng, Zhijie, et al.
Publicado: (2025)

CLUE: Conflict-guided Localization for LLM Unlearning Framework
por: Chen, Hang, et al.
Publicado: (2025)

On-the-fly Preference Alignment via Principle-Guided Decoding
por: Zhu, Mingye, et al.
Publicado: (2025)

Group Preference Alignment: Customized LLM Response Generation from In-Situ Conversations
por: Mondal, Ishani, et al.
Publicado: (2025)

Negating Negatives: Alignment with Human Negative Samples via Distributional Dispreference Optimization
por: Duan, Shitong, et al.
Publicado: (2024)

Adversarial Preference Optimization: Enhancing Your Alignment via RM-LLM Game
por: Cheng, Pengyu, et al.
Publicado: (2023)

TTPA: Token-level Tool-use Preference Alignment Training Framework with Fine-grained Evaluation
por: Huang, Chengrui, et al.
Publicado: (2025)

Improving LLM Unlearning Robustness via Random Perturbations
por: Huu-Tien, Dang, et al.
Publicado: (2025)

Representation-Guided Parameter-Efficient LLM Unlearning
por: Xiao, Zeguan, et al.
Publicado: (2026)

TokAlign++: Advancing Vocabulary Adaptation via Better Token Alignment
por: Li, Chong, et al.
Publicado: (2026)

StoicLLM: Preference Optimization for Philosophical Alignment in Small Language Models
por: Khan, Ishmam, et al.
Publicado: (2026)

Improving Conversational Abilities of Quantized Large Language Models via Direct Preference Alignment
por: Lee, Janghwan, et al.
Publicado: (2024)

Not Every Token Needs Forgetting: Selective Unlearning to Limit Change in Utility in Large Language Model Unlearning
por: Wan, Yixin, et al.
Publicado: (2025)

SPECTRA: Revealing the Full Spectrum of User Preferences via Distributional LLM Inference
por: Zhang, Luyang, et al.
Publicado: (2025)

Energy-Based Preference Model Offers Better Offline Alignment than the Bradley-Terry Preference Model
por: Hong, Yuzhong, et al.
Publicado: (2024)