Imagen de Portada

What Makes a Good Curriculum? Disentangling the Effects of Data Ordering on LLM Mathematical Reasoning

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Jia, Yaning, Zhang, Chunhui, Diao, Xingjian, Yuan, Xiangchi, Ouyang, Zhongyu, Ma, Chiyu, Vosoughi, Soroush
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Scaled Supervision is an Implicit Lipschitz Regularizer
por: Ouyang, Zhongyu, et al.
Publicado: (2025)

Judging the Judges: A Systematic Study of Position Bias in LLM-as-a-Judge
por: Shi, Lin, et al.
Publicado: (2024)

Growing Through Experience: Scaling Episodic Grounding in Language Models
por: Zhang, Chunhui, et al.
Publicado: (2025)

SoundMind: RL-Incentivized Logic Reasoning for Audio-Language Models
por: Diao, Xingjian, et al.
Publicado: (2025)

What Makes LLMs Effective Sequential Recommenders? A Study on Preference Intensity and Temporal Context
por: Ouyang, Zhongyu, et al.
Publicado: (2025)

Overcoming Multi-step Complexity in Multimodal Theory-of-Mind Reasoning: A Scalable Bayesian Planner
por: Zhang, Chunhui, et al.
Publicado: (2025)

Pretrained Image-Text Models are Secretly Video Captioners
por: Zhang, Chunhui, et al.
Publicado: (2025)

KCES: Training-Free Defense for Robust Graph Neural Networks via Kernel Complexity
por: Jia, Yaning, et al.
Publicado: (2025)

Temporal Working Memory: Query-Guided Segment Refinement for Enhanced Multimodal Understanding
por: Diao, Xingjian, et al.
Publicado: (2025)

Judging with Many Minds: Do More Perspectives Mean Less Prejudice? On Bias Amplifications and Resistance in Multi-Agent Based LLM-as-Judge
por: Ma, Chiyu, et al.
Publicado: (2025)

Music Audio-Visual Question Answering Requires Specialized Multimodal Designs
por: You, Wenhao, et al.
Publicado: (2025)

Superficial Self-Improved Reasoners Benefit from Model Merging
por: Yuan, Xiangchi, et al.
Publicado: (2025)

What Makes Good Multilingual Reasoning? Disentangling Reasoning Traces with Measurable Features
por: Ki, Dayeon, et al.
Publicado: (2026)

Non-parametric Graph Convolution for Re-ranking in Recommendation Systems
por: Ouyang, Zhongyu, et al.
Publicado: (2025)

Behavior Knowledge Merge in Reinforced Agentic Models
por: Yuan, Xiangchi, et al.
Publicado: (2026)

Achieving Domain-Independent Certified Robustness via Knowledge Continuity
por: Sun, Alan, et al.
Publicado: (2024)

Addressing Overthinking in Large Vision-Language Models via Gated Perception-Reasoning Optimization
por: Diao, Xingjian, et al.
Publicado: (2026)

ProtoVQA: An Adaptable Prototypical Framework for Explainable Fine-Grained Visual Question Answering
por: Diao, Xingjian, et al.
Publicado: (2025)

Towards Interpretable Deep Reinforcement Learning Models via Inverse Reinforcement Learning
por: Xie, Sean, et al.
Publicado: (2022)

Is It Navajo? Accurate Language Detection in Endangered Athabaskan Languages
por: Yang, Ivory, et al.
Publicado: (2025)

Probing Association Biases in LLM Moderation Over-Sensitivity
por: Wang, Yuxin, et al.
Publicado: (2025)

Feedforward Ordering in Neural Connectomes via Feedback Arc Minimization
por: Vahidi, Soroush
Publicado: (2025)

Semantic Compositions Enhance Vision-Language Contrastive Learning
por: Aladago, Maxwell, et al.
Publicado: (2024)

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

AlphaLoRA: Assigning LoRA Experts Based on Layer Training Quality
por: Qing, Peijun, et al.
Publicado: (2024)

Learning Musical Representations for Music Performance Question Answering
por: Diao, Xingjian, et al.
Publicado: (2025)

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

ActionCodec: What Makes for Good Action Tokenizers
por: Dong, Zibin, et al.
Publicado: (2026)

Serial Position Effects of Large Language Models
por: Guo, Xiaobo, et al.
Publicado: (2024)

Making Mathematical Reasoning Adaptive
por: Lai, Zhejian, et al.
Publicado: (2025)

Tracing LLM Reasoning Processes with Strategic Games: A Framework for Planning, Revision, and Resource-Constrained Decision Making
por: Yuan, Xiaopeng, et al.
Publicado: (2025)

What Makes In-context Learning Effective for Mathematical Reasoning: A Theoretical Analysis
por: Liu, Jiayu, et al.
Publicado: (2024)

GanitLLM: Difficulty-Aware Bengali Mathematical Reasoning through Curriculum-GRPO
por: Dipta, Shubhashis Roy, et al.
Publicado: (2026)

What Makes a Good Diffusion Planner for Decision Making?
por: Lu, Haofei, et al.
Publicado: (2025)

Interpretable Image Classification with Adaptive Prototype-based Vision Transformers
por: Ma, Chiyu, et al.
Publicado: (2024)

Bidirectional Curriculum Generation: A Multi-Agent Framework for Data-Efficient Mathematical Reasoning
por: Hu, Boren, et al.
Publicado: (2026)

SwiReasoning: Switch-Thinking in Latent and Explicit for Pareto-Superior Reasoning LLMs
por: Shi, Dachuan, et al.
Publicado: (2025)

What Makes a Good Query? Measuring the Impact of Human-Confusing Linguistic Features on LLM Performance
por: Watson, William, et al.
Publicado: (2026)

Cluster-R1: Large Reasoning Models Are Instruction-following Clustering Agents
por: Qing, Peijun, et al.
Publicado: (2026)

Deconstructing What Makes a Good Optimizer for Language Models
por: Zhao, Rosie, et al.
Publicado: (2024)