Cover Image

CAP: Controllable Alignment Prompting for Unlearning in LLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Zhaokun, Guo, Jinyu, Pu, Jingwen, Pu, Hongli, Yang, Meng, Chen, Xunlei, Ou, Jie, Li, Wenyi, Luo, Guangchun, Tian, Wenhong
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Noise-Robustness Through Noise: A Framework combining Asymmetric LoRA with Poisoning MoE
by: Wang, Zhaokun, et al.
Published: (2025)

ALTER: Asymmetric LoRA for Token-Entropy-Guided Unlearning of LLMs
by: Chen, Xunlei, et al.
Published: (2026)

AdapShot: Adaptive Many-Shot In-Context Learning with Semantic-Aware KV Cache Reuse
by: Ou, Jie, et al.
Published: (2026)

Accelerating Adaptive Retrieval Augmented Generation via Instruction-Driven Representation Reduction of Retrieval Overlaps
by: Ou, Jie, et al.
Published: (2025)

HASH-RAG: Bridging Deep Hashing with Retriever for Efficient, Fine Retrieval and Augmented Generation
by: Guo, Jinyu, et al.
Published: (2025)

How to Auto-optimize Prompts for Domain Tasks? Adaptive Prompting and Reasoning through Evolutionary Domain Knowledge Adaptation
by: Zhao, Yang, et al.
Published: (2025)

CAP-CoT: Cycle Adversarial Prompt for Improving Chain of Thoughts in LLM Reasoning
by: Chen, Shuxu, et al.
Published: (2026)

Neighbourhood Transformer: Switchable Attention for Monophily-Aware Graph Learning
by: Luo, Yi, et al.
Published: (2026)

PAD: Personalized Alignment of LLMs at Decoding-Time
by: Chen, Ruizhe, et al.
Published: (2024)

Evaluating LLMs for Text-to-SQL Generation With Complex SQL Workload
by: Ma, Limin, et al.
Published: (2024)

Agentic Unlearning: When LLM Agent Meets Machine Unlearning
by: Wang, Bin, et al.
Published: (2026)

Self-Correction as Feedback Control: Error Dynamics, Stability Thresholds, and Prompt Interventions in LLMs
by: Liu, Aofan, et al.
Published: (2026)

Generalizable Speech Deepfake Detection via Information Bottleneck Enhanced Adversarial Alignment
by: Huang, Pu, et al.
Published: (2025)

Understanding the Emergence of Multimodal Representation Alignment
by: Tjandrasuwita, Megan, et al.
Published: (2025)

Controllable Navigation Instruction Generation with Chain of Thought Prompting
by: Kong, Xianghao, et al.
Published: (2024)

OFFSIDE: Benchmarking Unlearning Misinformation in Multimodal Large Language Models
by: Zheng, Hao, et al.
Published: (2025)

From "Aha Moments" to Controllable Thinking: Toward Meta-Cognitive Reasoning in Large Reasoning Models via Decoupled Reasoning and Control
by: Ha, Rui, et al.
Published: (2025)

Hybrid Policy Distillation for LLMs
by: Zhu, Wenhong, et al.
Published: (2026)

Ignite Forecasting with SPARK: An Efficient Generative Framework for Refining LLMs in Temporal Knowledge Graph Forecasting
by: Yin, Gongzhu, et al.
Published: (2025)

Adapting and Evaluating Multimodal Large Language Models for Adolescent Idiopathic Scoliosis Self-Management: A Divide and Conquer Framework
by: Wu, Zhaolong, et al.
Published: (2025)

LMEraser: Large Model Unlearning through Adaptive Prompt Tuning
by: Xu, Jie, et al.
Published: (2024)

STAR: Similarity-guided Teacher-Assisted Refinement for Super-Tiny Function Calling Models
by: Ni, Jiliang, et al.
Published: (2026)

Prompt-Based Length Controlled Generation with Multiple Control Types
by: Jie, Renlong, et al.
Published: (2024)

From Black Box to Transparency: Enhancing Automated Interpreting Assessment with Explainable AI in College Classrooms
by: Jiang, Zhaokun, et al.
Published: (2025)

DP2Unlearning: An Efficient and Guaranteed Unlearning Framework for LLMs
by: Mahmud, Tamim Al, et al.
Published: (2025)

Fast and Accurate Probing of In-Training LLMs' Downstream Performances
by: Liu, Zhichen, et al.
Published: (2026)

ESP: Exploiting Symmetry Prior for Multi-Agent Reinforcement Learning
by: Yu, Xin, et al.
Published: (2023)

Relationship-Aware Safety Unlearning for Multimodal LLMs
by: Anilkumar, Vishnu Narayanan, et al.
Published: (2026)

MoColl: Agent-Based Specific and General Model Collaboration for Image Captioning
by: Yang, Pu, et al.
Published: (2025)

Predicting Performance of Symbolic and Prompt Programs with Examples
by: Zheng, Chengqi, et al.
Published: (2026)

Spatiotemporal Prediction of Secondary Crashes by Rebalancing Dynamic and Static Data with Generative Adversarial Networks
by: Chen, Junlan, et al.
Published: (2025)

ZSPAPrune: Zero-Shot Prompt-Aware Token Pruning for Vision-Language Models
by: Zhang, Pu, et al.
Published: (2025)

Vision-Based Generic Potential Function for Policy Alignment in Multi-Agent Reinforcement Learning
by: Ma, Hao, et al.
Published: (2025)

GAC: Stabilizing Asynchronous RL Training for LLMs via Gradient Alignment Control
by: Xu, Haofeng, et al.
Published: (2026)

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

PolicyEvolve: Evolving Programmatic Policies by LLMs for multi-player games via Population-Based Training
by: Lv, Mingrui, et al.
Published: (2025)

Enhancing LLMs for Time Series Forecasting via Structure-Guided Cross-Modal Alignment
by: Sun, Siming, et al.
Published: (2025)

EvoPrompt: Connecting LLMs with Evolutionary Algorithms Yields Powerful Prompt Optimizers
by: Guo, Qingyan, et al.
Published: (2023)

Machine Unlearning with Minimal Gradient Dependence for High Unlearning Ratios
by: Huang, Tao, et al.
Published: (2024)

Unified Parameter-Efficient Unlearning for LLMs
by: Ding, Chenlu, et al.
Published: (2024)