Probing Knowledge Holes in Unlearned LLMs
"知识保留" 相关文章
Adapting Large Language Models to Emerging Cybersecurity using Retrieval Augmented Generation
Don't Blind Your VLA: Aligning Visual Representations for OOD Generalization
Beyond Reasoning Gains: Mitigating General Capabilities Forgetting in Large Reasoning Models
RECALL: REpresentation-aligned Catastrophic-forgetting ALLeviation via Hierarchical Model Merging
RECALL: REpresentation-aligned Catastrophic-forgetting ALLeviation via Hierarchical Model Merging
AI重塑大学课堂：是“超级助手”还是“思考终结者”？
Contextual Attention Modulation: Towards Efficient Multi-Task Adaptation in Large Language Models
The Choice of Divergence: A Neglected Key to Mitigating Diversity Collapse in Reinforcement Learning with Verifiable Reward
TRCE: Towards Reliable Malicious Concept Erasure in Text-to-Image Diffusion Models
A Design is a Mold for Code
P2DT: Mitigating Forgetting in task-incremental Learning with progressive prompt Decision Transformer
Application Of Large Language Models For The Extraction Of Information From Particle Accelerator Technical Documentation
Retention analysis of edited knowledge after fine-tuning
eSapiens: A Platform for Secure and Auditable Retrieval-Augmented Generation
Reinforcement Fine-Tuning Naturally Mitigates Forgetting in Continual Post-Training
This AI Paper from KAIST, UCL and KT Investigates the Acquisition and Retention of Factual Knowledge in Large Language Models
