Cover Image

Why Supervised Fine-Tuning Fails to Learn: A Systematic Study of Incomplete Learning in Large Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Xue, Chao, Wang, Yao, Liu, Mengqiao, Liang, Di, Han, Xingsheng, Liu, Peiyang, Wu, Xianjie, Lu, Chenyao, Jiang, Lei, Lu, Yu, Shi, Haibo, Liang, Shuang, Peng, Minlong, Salim, Flora D.
Format:	Preprint
Published:	2026
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Parameter Importance is Not Static: Evolving Parameter Isolation for Supervised Fine-Tuning
by: Lin, Zekai, et al.
Published: (2026)

Reason Only When Needed: Efficient Generative Reward Modeling via Model-Internal Uncertainty
by: Xue, Chao, et al.
Published: (2026)

Not All Parameters Are Created Equal: Smart Isolation Boosts Fine-Tuning Performance
by: Wang, Yao, et al.
Published: (2025)

DPI: Exploiting Parameter Heterogeneity for Interference-Free Fine-Tuning
by: Liu, Xiaoyu, et al.
Published: (2026)

DeCoRL: Decoupling Reasoning Chains via Parallel Sub-Step Generation and Cascaded Reinforcement for Interpretable and Scalable RLHF
by: Gao, Ziyuan, et al.
Published: (2025)

CoughViT: A Self-Supervised Vision Transformer for Cough Audio Representation Learning
by: Luong, Justin, et al.
Published: (2025)

Structural Reward Model: Enhancing Interpretability, Efficiency, and Scalability in Reward Modeling
by: Liu, Xiaoyu, et al.
Published: (2025)

TRACE: Discovering Task-Specific Parameter via Adaptation-Aware Probing for Continual Fine-Tuning
by: Han, Xiaosong, et al.
Published: (2026)

Spectral Sensitivity of Directed Weighted Networks: Why Weakening Edges May Trigger Synchronization
by: Wu, Xinyu, et al.
Published: (2026)

SplitFT: An Adaptive Federated Split Learning System For LLMs Fine-Tuning
by: Shan, Yimeng, et al.
Published: (2026)

Proximal Supervised Fine-Tuning
by: Zhu, Wenhong, et al.
Published: (2025)

Refine-POI: Reinforcement Fine-Tuned Large Language Models for Next Point-of-Interest Recommendation
by: Li, Peibo, et al.
Published: (2025)

Reinforcement Learning Enhanced Multi-hop Reasoning for Temporal Knowledge Question Answering
by: Wen, Wuzhenghong, et al.
Published: (2026)

Why Bonds Fail Differently? Explainable Multimodal Learning for Multi-Class Default Prediction
by: Lu, Yi, et al.
Published: (2025)

CP-MoE: Consistency-Preserving Mixture-of-Experts for Continual Learning
by: Liu, Yang, et al.
Published: (2026)

Who Stole Your Data? A Method for Detecting Unauthorized RAG Theft
by: Liu, Peiyang, et al.
Published: (2025)

Rotation-Preserving Supervised Fine-Tuning
by: Jin, Hangzhan, et al.
Published: (2026)

DeepLévy: Learning Heavy-Tailed Uncertainty in Highly Volatile Time Series
by: Yang, Yang, et al.
Published: (2026)

Supervised Fine-Tuning as Inverse Reinforcement Learning
by: Sun, Hao
Published: (2024)

Understanding Server-Assisted Federated Learning in the Presence of Incomplete Client Participation
by: Yang, Haibo, et al.
Published: (2024)

Unlock the Correlation between Supervised Fine-Tuning and Reinforcement Learning in Training Code Large Language Models
by: Chen, Jie, et al.
Published: (2024)

Simultaneous Computation and Memory Efficient Zeroth-Order Optimizer for Fine-Tuning Large Language Models
by: Wang, Fei, et al.
Published: (2024)

DRIFT-Net: A Spectral--Coupled Neural Operator for PDEs Learning
by: Li, Jiayi, et al.
Published: (2025)

Why Attention Fails: The Degeneration of Transformers into MLPs in Time Series Forecasting
by: Liang, Zida, et al.
Published: (2025)

CGM-JEPA: Learning Consistent Continuous Glucose Monitor Representations via Predictive Self-Supervised Pretraining
by: Muhammad, Hada Melino, et al.
Published: (2026)

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

Token Cleaning: Fine-Grained Data Selection for LLM Supervised Fine-Tuning
by: Pang, Jinlong, et al.
Published: (2025)

Learning from Contrasts: Synthesizing Reasoning Paths from Diverse Search Trajectories
by: Liu, Peiyang, et al.
Published: (2026)

Zero-Shot Cross-Domain Code Search without Fine-Tuning
by: Liang, Keyu, et al.
Published: (2025)

From XXLTraffic to EvoXXLTraffic: Scaling Traffic Forecasting to Sensor-Evolving Networks
by: Yin, Du, et al.
Published: (2026)

XXLTraffic: Expanding and Extremely Long Traffic forecasting beyond test adaptation
by: Yin, Du, et al.
Published: (2024)

HiT-JEPA: A Hierarchical Self-supervised Trajectory Embedding Framework for Similarity Computation
by: Li, Lihuan, et al.
Published: (2025)

HLoRA: Efficient Federated Learning System for LLM Heterogeneous Fine-Tuning
by: Liu, Qianli, et al.
Published: (2025)

In-Context Learning Distillation for Efficient Few-Shot Fine-Tuning
by: Duan, Yifei, et al.
Published: (2024)

Enhancing Spatio-temporal Quantile Forecasting with Curriculum Learning: Lessons Learned
by: Yin, Du, et al.
Published: (2024)

EMAC+: Embodied Multimodal Agent for Collaborative Planning with VLM+LLM
by: Ao, Shuang, et al.
Published: (2025)

Learning Through Noise: Why Subliminal Learning Works and When It Fails
by: Brockers, Vincent C., et al.
Published: (2026)

Reassessing the Role of Supervised Fine-Tuning: An Empirical Study in VLM Reasoning
by: Yu, Yongcan, et al.
Published: (2025)

PASCL: Supervised Contrastive Learning with Perturbative Augmentation for Particle Decay Reconstruction
by: Lu, Junjian, et al.
Published: (2024)

UFT: Unifying Supervised and Reinforcement Fine-Tuning
by: Liu, Mingyang, et al.
Published: (2025)