Copertina

Data Difficulty and the Generalization--Extrapolation Tradeoff in LLM Fine-Tuning

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Liu, Siyuan, Chen, Tinghong, Li, Xinghan, Wang, Yifei, Zhang, Jingzhao
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

FT-Dojo: Towards Autonomous LLM Fine-Tuning with Language Agents
di: Li, Qizheng, et al.
Pubblicazione: (2026)

Random Masking Finds Winning Tickets for Parameter Efficient Fine-tuning
di: Xu, Jing, et al.
Pubblicazione: (2024)

Adaptive Ensembles of Fine-Tuned Transformers for LLM-Generated Text Detection
di: Lai, Zhixin, et al.
Pubblicazione: (2024)

Improving Data Efficiency for LLM Reinforcement Fine-tuning Through Difficulty-targeted Online Data Selection and Rollout Replay
di: Sun, Yifan, et al.
Pubblicazione: (2025)

MathMixup: Boosting LLM Mathematical Reasoning with Difficulty-Controllable Data Synthesis and Curriculum Learning
di: Li, Xuchen, et al.
Pubblicazione: (2026)

SRFT: A Single-Stage Method with Supervised and Reinforcement Fine-Tuning for Reasoning
di: Fu, Yuqian, et al.
Pubblicazione: (2025)

Alignment Dynamics in LLM Fine-Tuning
di: Huang, Yuhan, et al.
Pubblicazione: (2026)

Implicit Federated In-context Learning For Task-Specific LLM Fine-Tuning
di: Li, Dongcheng, et al.
Pubblicazione: (2025)

LoX: Low-Rank Extrapolation Robustifies LLM Safety Against Fine-tuning
di: Perin, Gabriel J., et al.
Pubblicazione: (2025)

Selection of LLM Fine-Tuning Data based on Orthogonal Rules
di: Li, Xiaomin, et al.
Pubblicazione: (2024)

On the Condition Number Dependency in Bilevel Optimization
di: Chen, Lesi, et al.
Pubblicazione: (2025)

MoFO: Momentum-Filtered Optimizer for Mitigating Forgetting in LLM Fine-Tuning
di: Chen, Yupeng, et al.
Pubblicazione: (2024)

H2Tune: Federated Foundation Model Fine-Tuning with Hybrid Heterogeneity
di: Guo, Wei, et al.
Pubblicazione: (2025)

Goal-Conditioned Supervised Learning for LLM Fine-Tuning
di: Li, Shijun, et al.
Pubblicazione: (2026)

DipLLM: Fine-Tuning LLM for Strategic Decision-making in Diplomacy
di: Xu, Kaixuan, et al.
Pubblicazione: (2025)

LENSLLM: Unveiling Fine-Tuning Dynamics for LLM Selection
di: Zeng, Xinyue, et al.
Pubblicazione: (2025)

Data Mixing Can Induce Phase Transitions in Knowledge Acquisition
di: Gu, Xinran, et al.
Pubblicazione: (2025)

Children's English Reading Story Generation via Supervised Fine-Tuning of Compact LLMs with Controllable Difficulty and Safety
di: Shen, Qian, et al.
Pubblicazione: (2026)

MallowsPO: Fine-Tune Your LLM with Preference Dispersions
di: Chen, Haoxian, et al.
Pubblicazione: (2024)

Beyond the Dirac Delta: Mitigating Diversity Collapse in Reinforcement Fine-Tuning for Versatile Image Generation
di: Liu, Jinmei, et al.
Pubblicazione: (2026)

Silent Inconsistency in Data-Parallel Full Fine-Tuning: Diagnosing Worker-Level Optimization Misalignment
di: Li, Hong, et al.
Pubblicazione: (2026)

Towards Mitigation of Hallucination for LLM-empowered Agents: Progressive Generalization Bound Exploration and Watchdog Monitor
di: Liu, Siyuan, et al.
Pubblicazione: (2025)

From Parameter Dynamics to Risk Scoring : Quantifying Sample-Level Safety Degradation in LLM Fine-tuning
di: Wang, Xiao, et al.
Pubblicazione: (2026)

Filter-then-Weight: Online Data Selection and Reweighting for LLM Fine-Tuning
di: Wang, Fangxin, et al.
Pubblicazione: (2026)

RoRA: Efficient Fine-Tuning of LLM with Reliability Optimization for Rank Adaptation
di: Liu, Jun, et al.
Pubblicazione: (2025)

Fine-Tune an SLM or Prompt an LLM? The Case of Generating Low-Code Workflows
di: Ayala, Orlando Marquez, et al.
Pubblicazione: (2025)

Internalizing Curriculum Judgment for LLM Reinforcement Fine-Tuning
di: Zheng, Han, et al.
Pubblicazione: (2026)

Overcoming Forgetting in LLM Fine-Tuning with Evolution Strategies
di: Schweighofer, Kajetan, et al.
Pubblicazione: (2026)

CurvZO: Adaptive Curvature-Guided Sparse Zeroth-Order Optimization for Efficient LLM Fine-Tuning
di: Wang, Shuo, et al.
Pubblicazione: (2026)

On the Entropy Dynamics in Reinforcement Fine-Tuning of Large Language Models
di: Wang, Shumin, et al.
Pubblicazione: (2026)

KALIE: Fine-Tuning Vision-Language Models for Open-World Manipulation without Robot Data
di: Tang, Grace, et al.
Pubblicazione: (2024)

On Finding Small Hyper-Gradients in Bilevel Optimization: Hardness Results and Improved Analysis
di: Chen, Lesi, et al.
Pubblicazione: (2023)

OAT-Rephrase: Optimization-Aware Training Data Rephrasing for Zeroth-Order LLM Fine-Tuning
di: Long, Jikai, et al.
Pubblicazione: (2025)

From Theory to Application: Fine-Tuning Large EEG Model with Real-World Stress Data
di: Wang, Siwen, et al.
Pubblicazione: (2025)

Mitigating Non-IID Drift in Zeroth-Order Federated LLM Fine-Tuning with Transferable Sparsity
di: Ran, Yide, et al.
Pubblicazione: (2025)

Understanding and Preserving Safety in Fine-Tuned LLMs
di: Zhang, Jiawen, et al.
Pubblicazione: (2026)

Forget the Data and Fine-Tuning! Just Fold the Network to Compress
di: Wang, Dong, et al.
Pubblicazione: (2025)

Mesa-Extrapolation: A Weave Position Encoding Method for Enhanced Extrapolation in LLMs
di: Ma, Xin, et al.
Pubblicazione: (2024)

SafeTuneBed: A Toolkit for Benchmarking LLM Safety Alignment in Fine-Tuning
di: Hossain, Saad, et al.
Pubblicazione: (2025)

Wireless Federated Multi-Task LLM Fine-Tuning via Sparse-and-Orthogonal LoRA
di: Yang, Nuocheng, et al.
Pubblicazione: (2026)