Copertina

Unlocking the Power of Function Vectors for Characterizing and Mitigating Catastrophic Forgetting in Continual Instruction Tuning

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Jiang, Gangwei, Jiang, Caigao, Li, Zhaoyi, Xue, Siqiao, Zhou, Jun, Song, Linqi, Lian, Defu, Wei, Ying
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Refine Large Language Model Fine-tuning via Instruction Vector
di: Jiang, Gangwei, et al.
Pubblicazione: (2024)

Understanding and Patching Compositional Reasoning in LLMs
di: Li, Zhaoyi, et al.
Pubblicazione: (2024)

Scaling Reasoning Hop Exposes Weaknesses: Demystifying and Improving Hop Generalization in Large Language Models
di: Li, Zhaoyi, et al.
Pubblicazione: (2026)

Mitigate Negative Transfer with Similarity Heuristic Lifelong Prompt Tuning
di: Wu, Chenyuan, et al.
Pubblicazione: (2024)

On the Role of Reasoning Patterns in the Generalization Discrepancy of Long Chain-of-Thought Supervised Fine-Tuning
di: Li, Zhaoyi, et al.
Pubblicazione: (2026)

What Makes a Good Reasoning Chain? Uncovering Structural Patterns in Long Chain-of-Thought Reasoning
di: Jiang, Gangwei, et al.
Pubblicazione: (2025)

Mitigating the Language Mismatch and Repetition Issues in LLM-based Machine Translation via Model Editing
di: Wang, Weichuan, et al.
Pubblicazione: (2024)

Learning to Substitute Components for Compositional Generalization
di: Li, Zhaoyi, et al.
Pubblicazione: (2025)

Catastrophic Forgetting Mitigation via Discrepancy-Weighted Experience Replay
di: Xu, Xinrun, et al.
Pubblicazione: (2025)

Benchmarking and Improving Compositional Generalization of Multi-aspect Controllable Text Generation
di: Zhong, Tianqi, et al.
Pubblicazione: (2024)

CURLoRA: Stable LLM Continual Fine-Tuning and Catastrophic Forgetting Mitigation
di: Fawi, Muhammad
Pubblicazione: (2024)

Sequencing to Mitigate Catastrophic Forgetting in Continual Learning
di: Moussa, Hesham G., et al.
Pubblicazione: (2025)

Dynamic Orthogonal Continual Fine-tuning for Mitigating Catastrophic Forgettings
di: Zhang, Zhixin, et al.
Pubblicazione: (2025)

SMoLoRA: Exploring and Defying Dual Catastrophic Forgetting in Continual Visual Instruction Tuning
di: Wang, Ziqi, et al.
Pubblicazione: (2024)

Mitigating Catastrophic Forgetting in Large Language Models with Forgetting-aware Pruning
di: Huang, Wei, et al.
Pubblicazione: (2025)

Mitigating Catastrophic Forgetting in Continual Learning through Model Growth
di: Süalp, Ege, et al.
Pubblicazione: (2025)

Continual Learning and Catastrophic Forgetting
di: van de Ven, Gido M., et al.
Pubblicazione: (2024)

Continual Deep Reinforcement Learning to Prevent Catastrophic Forgetting in Jamming Mitigation
di: Davaslioglu, Kemal, et al.
Pubblicazione: (2024)

CORE: Mitigating Catastrophic Forgetting in Continual Learning through Cognitive Replay
di: Zhang, Jianshu, et al.
Pubblicazione: (2024)

Mitigating Catastrophic Forgetting with Adaptive Transformer Block Expansion in Federated Fine-Tuning
di: Huo, Yujia, et al.
Pubblicazione: (2025)

Improved Supervised Fine-Tuning for Large Language Models to Mitigate Catastrophic Forgetting
di: Ding, Fei, et al.
Pubblicazione: (2025)

Overcoming Catastrophic Forgetting in Visual Continual Learning with Reinforcement Fine-Tuning
di: Lou, Meng, et al.
Pubblicazione: (2026)

Analyzing and Reducing Catastrophic Forgetting in Parameter Efficient Tuning
di: Ren, Weijieying, et al.
Pubblicazione: (2024)

Sharpness-Aware Pretraining Mitigates Catastrophic Forgetting
di: Watts, Ishaan, et al.
Pubblicazione: (2026)

Spatiotemporal Continual Learning for Mobile Edge UAV Networks: Mitigating Catastrophic Forgetting
di: Lai, Chuan-Chi
Pubblicazione: (2026)

Mitigating Catastrophic Forgetting in Multi-domain Chinese Spelling Correction by Multi-stage Knowledge Transfer Framework
di: Xing, Peng, et al.
Pubblicazione: (2024)

Mitigating Catastrophic Forgetting in the Incremental Learning of Medical Images
di: Yavari, Sara, et al.
Pubblicazione: (2025)

PACIT: Unlocking the Power of Examples for Better In-Context Instruction Tuning
di: Xue, Tianci, et al.
Pubblicazione: (2023)

Mitigating Catastrophic Forgetting in Large Language Models with Self-Synthesized Rehearsal
di: Huang, Jianheng, et al.
Pubblicazione: (2024)

Revisiting Catastrophic Forgetting in Large Language Model Tuning
di: Li, Hongyu, et al.
Pubblicazione: (2024)

Exploring Kolmogorov-Arnold Network Expansions in Vision Transformers for Mitigating Catastrophic Forgetting in Continual Learning
di: Ullah, Zahid, et al.
Pubblicazione: (2025)

Mitigating Catastrophic Forgetting in Language Transfer via Model Merging
di: Alexandrov, Anton, et al.
Pubblicazione: (2024)

Catastrophic Forgetting Mitigation Through Plateau Phase Activity Profiling
di: Mashiach, Idan, et al.
Pubblicazione: (2025)

Reinforcement Fine-Tuning Naturally Mitigates Forgetting in Continual Post-Training
di: Lai, Song, et al.
Pubblicazione: (2025)

Balancing Speciality and Versatility: A Coarse to Fine Framework for Mitigating Catastrophic Forgetting in Large Language Models
di: Zhang, Hengyuan, et al.
Pubblicazione: (2024)

Bayesian Parameter-Efficient Fine-Tuning for Overcoming Catastrophic Forgetting
di: Chen, Haolin, et al.
Pubblicazione: (2024)

Addressing Loss of Plasticity and Catastrophic Forgetting in Continual Learning
di: Elsayed, Mohamed, et al.
Pubblicazione: (2024)

Revisiting Catastrophic Forgetting in Continual Knowledge Graph Embedding
di: Pons, Gerard, et al.
Pubblicazione: (2026)

On the Implicit Adversariality of Catastrophic Forgetting in Deep Continual Learning
di: Peng, Ze, et al.
Pubblicazione: (2025)

ROMAS: A Role-Based Multi-Agent System for Database monitoring and Planning
di: Huang, Yi, et al.
Pubblicazione: (2024)