Buchumschlag

Extend Model Merging from Fine-Tuned to Pre-Trained Large Language Models via Weight Disentanglement

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Yu, Le, Yu, Bowen, Yu, Haiyang, Huang, Fei, Li, Yongbin
Format:	Preprint
Veröffentlicht:	2024
Schlagworte:	Computation and Language
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch
von: Yu, Le, et al.
Veröffentlicht: (2023)

Scaling Data Diversity for Fine-Tuning Language Models in Human Alignment
von: Song, Feifan, et al.
Veröffentlicht: (2024)

Fine-Tuning Language Models with Reward Learning on Policy
von: Lang, Hao, et al.
Veröffentlicht: (2024)

EIFBENCH: Extremely Complex Instruction Following Benchmark for Large Language Models
von: Zou, Tao, et al.
Veröffentlicht: (2025)

Self-Retrieval: End-to-End Information Retrieval with One Large Language Model
von: Tang, Qiaoyu, et al.
Veröffentlicht: (2024)

Iterative Forward Tuning Boosts In-Context Learning in Language Models
von: Yang, Jiaxi, et al.
Veröffentlicht: (2023)

Safeguard Fine-Tuned LLMs Through Pre- and Post-Tuning Model Merging
von: Farn, Hua, et al.
Veröffentlicht: (2024)

Preference Ranking Optimization for Human Alignment
von: Song, Feifan, et al.
Veröffentlicht: (2023)

A Preliminary Study of the Intrinsic Relationship between Complexity and Alignment
von: Zhao, Yingxiu, et al.
Veröffentlicht: (2023)

IOPO: Empowering LLMs with Complex Instruction Following via Input-Output Preference Optimization
von: Zhang, Xinghua, et al.
Veröffentlicht: (2024)

DEMO: Reframing Dialogue Interaction with Fine-grained Element Modeling
von: Wang, Minzheng, et al.
Veröffentlicht: (2024)

SoFA: Shielded On-the-fly Alignment via Priority Rule Following
von: Lu, Xinyu, et al.
Veröffentlicht: (2024)

Legal Documents Drafting with Fine-Tuned Pre-Trained Large Language Model
von: Lin, Chun-Hsien, et al.
Veröffentlicht: (2024)

HFT: Half Fine-Tuning for Large Language Models
von: Hui, Tingfeng, et al.
Veröffentlicht: (2024)

On the Role of Attention Heads in Large Language Model Safety
von: Zhou, Zhenhong, et al.
Veröffentlicht: (2024)

Empirical Analysis of Efficient Fine-Tuning Methods for Large Pre-Trained Language Models
von: Doering, Nigel, et al.
Veröffentlicht: (2024)

Multi-Task Model Merging via Adaptive Weight Disentanglement
von: Xiong, Feng, et al.
Veröffentlicht: (2024)

Decouple Searching from Training: Scaling Data Mixing via Model Merging for Large Language Model Pre-training
von: Li, Shengrui, et al.
Veröffentlicht: (2026)

Model Merging in Pre-training of Large Language Models
von: Li, Yunshui, et al.
Veröffentlicht: (2025)

Amuro and Char: Analyzing the Relationship between Pre-Training and Fine-Tuning of Large Language Models
von: Sun, Kaiser, et al.
Veröffentlicht: (2024)

Transferable Post-training via Inverse Value Learning
von: Lu, Xinyu, et al.
Veröffentlicht: (2024)

The Imperative of Conversation Analysis in the Era of LLMs: A Survey of Tasks, Techniques, and Trends
von: Zhang, Xinghua, et al.
Veröffentlicht: (2024)

Parameter-Efficient Fine-Tuning of Large Language Models via Deconvolution in Subspace
von: Zhang, Jia-Chen, et al.
Veröffentlicht: (2025)

Recovering the Pre-Fine-Tuning Weights of Generative Models
von: Horwitz, Eliahu, et al.
Veröffentlicht: (2024)

On the Limits of Model Merging for Multilinguality in Pre-Training
von: Aycock, Seth, et al.
Veröffentlicht: (2026)

Dynamics of Instruction Fine-Tuning for Chinese Large Language Models
von: Song, Chiyu, et al.
Veröffentlicht: (2023)

Reversing Large Language Models for Efficient Training and Fine-Tuning
von: Gal, Eshed, et al.
Veröffentlicht: (2025)

Speech-FT: Merging Pre-trained And Fine-Tuned Speech Representation Models For Cross-Task Generalization
von: Lin, Tzu-Quan, et al.
Veröffentlicht: (2025)

SafeMERGE: Preserving Safety Alignment in Fine-Tuned Large Language Models via Selective Layer-Wise Model Merging
von: Djuhera, Aladin, et al.
Veröffentlicht: (2025)

Consensus-Aligned Neuron Efficient Fine-Tuning Large Language Models for Multi-Domain Machine Translation
von: Jiang, Shuting, et al.
Veröffentlicht: (2026)

Disentangling Language and Culture for Evaluating Multilingual Large Language Models
von: Ying, Jiahao, et al.
Veröffentlicht: (2025)

Socratic-PRMBench: Benchmarking Process Reward Models with Systematic Reasoning Patterns
von: Li, Xiang, et al.
Veröffentlicht: (2025)

DeepSolution: Boosting Complex Engineering Solution Design via Tree-based Exploration and Bi-point Thinking
von: Li, Zhuoqun, et al.
Veröffentlicht: (2025)

Levels of AI Agents: from Rules to Large Language Models
von: Huang, Yu
Veröffentlicht: (2024)

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

Fine-Tuning Pre-Trained Code Models for AI-Generated Code Detection
von: Ispas, Jany-Gabriel, et al.
Veröffentlicht: (2026)

DEFT: Data Efficient Fine-Tuning for Pre-Trained Language Models via Unsupervised Core-Set Selection
von: Das, Devleena, et al.
Veröffentlicht: (2023)

A Unified View of Delta Parameter Editing in Post-Trained Large-Scale Models
von: Tang, Qiaoyu, et al.
Veröffentlicht: (2024)

OWQ: Outlier-Aware Weight Quantization for Efficient Fine-Tuning and Inference of Large Language Models
von: Lee, Changhun, et al.
Veröffentlicht: (2023)

SVFit: Parameter-Efficient Fine-Tuning of Large Pre-Trained Models Using Singular Values
von: Sun, Chengwei, et al.
Veröffentlicht: (2024)