Imagen de Portada

Towards Order Fairness: Mitigating LLMs Order Sensitivity through Dual Group Advantage Optimization

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Chu, Xu, Wang, Guanyu, Tan, Zhijie, Chen, Xinrong, Li, Ziyu, Mo, Tong, Li, Weiping
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

GraphSOS: Graph Sampling and Order Selection to Help LLMs Understand Graphs Better
por: Chu, Xu, et al.
Publicado: (2025)

Order Matters: Exploring Order Sensitivity in Multimodal Large Language Models
por: Tan, Zhijie, et al.
Publicado: (2024)

Qwen Look Again: Guiding Vision-Language Reasoning Models to Re-attention Visual Information
por: Chu, Xu, et al.
Publicado: (2025)

Domaino1s: Guiding LLM Reasoning for Explainable Answers in High-Stakes Domains
por: Chu, Xu, et al.
Publicado: (2025)

Adaptive Spatiotemporal Augmentation for Improving Dynamic Graph Learning
por: Chu, Xu, et al.
Publicado: (2025)

Advantage Collapse in Group Relative Policy Optimization: Diagnosis and Mitigation
por: He, Xixiang, et al.
Publicado: (2026)

Towards Fast LLM Fine-tuning through Zeroth-Order Optimization with Projected Gradient-Aligned Perturbations
por: Mi, Zhendong, et al.
Publicado: (2025)

Mitigating Task-Order Sensitivity and Forgetting via Hierarchical Second-Order Consolidation
por: Nag, Protik, et al.
Publicado: (2026)

Benchmarking Bias Mitigation Toward Fairness Without Harm from Vision to LVLMs
por: Tan, Xuwei, et al.
Publicado: (2026)

MEGA: Second-Order Gradient Alignment for Catastrophic Forgetting Mitigation in GFSCIL
por: Pang, Jinhui, et al.
Publicado: (2025)

Towards Group Fairness with Multiple Sensitive Attributes in Federated Foundation Models
por: Yang, Yuning, et al.
Publicado: (2025)

Learning a Zeroth-Order Optimizer for Fine-Tuning LLMs
por: Zhang, Kairun, et al.
Publicado: (2025)

AdaMeZO: Adam-style Zeroth-Order Optimizer for LLM Fine-tuning Without Maintaining the Moments
por: Cai, Zhijie, et al.
Publicado: (2026)

The Actor-Critic Update Order Matters for PPO in Federated Reinforcement Learning
por: Xie, Zhijie, et al.
Publicado: (2025)

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

Identification and Estimation of Simultaneous Equation Models Using Higher-Order Cumulant Restrictions
por: Jiang, Ziyu
Publicado: (2025)

A Fully First-Order Layer for Differentiable Optimization
por: Zhao, Zihao, et al.
Publicado: (2025)

Second-Order Fine-Tuning without Pain for LLMs:A Hessian Informed Zeroth-Order Optimizer
por: Zhao, Yanjun, et al.
Publicado: (2024)

Diversity Drives Fairness: Ensemble of Higher Order Mutants for Intersectional Fairness of Machine Learning Software
por: Chen, Zhenpeng, et al.
Publicado: (2024)

Fair Conformal Classification via Learning Representation-Based Groups
por: Xu, Senrong, et al.
Publicado: (2026)

Private Zeroth-Order Optimization with Public Data
por: Gong, Xuchen, et al.
Publicado: (2025)

GAGPO: Generalized Advantage Grouped Policy Optimization
por: Zhu, Siyuan, et al.
Publicado: (2026)

Bridging Jensen Gap for Max-Min Group Fairness Optimization in Recommendation
por: Xu, Chen, et al.
Publicado: (2025)

SEHFS: Structural Entropy-Guided High-Order Correlation Learning for Multi-View Multi-Label Feature Selection
por: Peng, Cheng, et al.
Publicado: (2026)

On the Parameterization of Second-Order Optimization Effective Towards the Infinite Width
por: Ishikawa, Satoki, et al.
Publicado: (2023)

The Power of Order: Fooling LLMs with Adversarial Table Permutations
por: Dong, Xinshuai, et al.
Publicado: (2026)

Privacy Amplification in Differentially Private Zeroth-Order Optimization with Hidden States
por: Chien, Eli, et al.
Publicado: (2025)

TeZO: Empowering the Low-Rankness on the Temporal Dimension in the Zeroth-Order Optimization for Fine-tuning LLMs
por: Sun, Yan, et al.
Publicado: (2025)

Towards Flash Thinking via Decoupled Advantage Policy Optimization
por: Tan, Zezhong, et al.
Publicado: (2025)

Your Group-Relative Advantage Is Biased
por: Yang, Fengkai, et al.
Publicado: (2026)

More Than Memory Savings: Zeroth-Order Optimization Mitigates Forgetting in Continual Learning
por: Yu, Wanhao, et al.
Publicado: (2025)

The Multi-Query Paradox in Zeroth-Order Optimization
por: Lin, Wei, et al.
Publicado: (2025)

Fairness without Sensitive Attributes via Knowledge Sharing
por: Ni, Hongliang, et al.
Publicado: (2024)

Fractional Order Distributed Optimization
por: Lixandru, Andrei, et al.
Publicado: (2024)

FairCauseSyn: Towards Causally Fair LLM-Augmented Synthetic Data Generation
por: Nagesh, Nitish, et al.
Publicado: (2025)

Zeroth-Order Fine-Tuning of LLMs in Random Subspaces
por: Yu, Ziming, et al.
Publicado: (2024)

Gradient Compressed Sensing: A Query-Efficient Gradient Estimator for High-Dimensional Zeroth-Order Optimization
por: Qiu, Ruizhong, et al.
Publicado: (2024)

Learning Dynamics of Zeroth-Order Optimization: A Kernel Perspective
por: Li, Zhe, et al.
Publicado: (2026)

Zeroth-Order Fine-Tuning of LLMs with Extreme Sparsity
por: Guo, Wentao, et al.
Publicado: (2024)

Accelerated Fully First-Order Methods for Bilevel and Minimax Optimization
por: Li, Chris Junchi
Publicado: (2024)