Imagen de Portada

Principled Understanding of Generalization for Generative Transformer Models in Arithmetic Reasoning Tasks

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Xu, Xingcheng, Zhao, Zibo, Zhang, Haipeng, Yang, Yanqing
Formato:	Preprint
Publicado:	2024
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

It Ain't That Bad: Understanding the Mysterious Performance Drop in OOD Generalization for Generative Transformer Models
por: Xu, Xingcheng, et al.
Publicado: (2023)

The Two-Stage Decision-Sampling Hypothesis: Understanding the Emergence of Self-Reflection in RL-Trained LLMs
por: Zhao, Zibo, et al.
Publicado: (2026)

Position Coupling: Improving Length Generalization of Arithmetic Transformers Using Task Structure
por: Cho, Hanseul, et al.
Publicado: (2024)

Toward a Unified Geometry Understanding: Riemannian Diffusion Framework for Graph Generation and Prediction
por: Gao, Yisen, et al.
Publicado: (2025)

Bus-Conditioned Zero-Shot Trajectory Generation via Task Arithmetic
por: Liu, Shuai, et al.
Publicado: (2026)

Epistemic Traps: Rational Misalignment Driven by Model Misspecification
por: Xu, Xingcheng, et al.
Publicado: (2026)

The Policy Cliff: A Theoretical Analysis of Reward-Policy Maps in Large Language Models
por: Xu, Xingcheng
Publicado: (2025)

Arithmetic Transformers Can Length-Generalize in Both Operand Length and Count
por: Cho, Hanseul, et al.
Publicado: (2024)

Language Models Do Hard Arithmetic Tasks Easily and Hardly Do Easy Arithmetic Tasks
por: Gambardella, Andrew, et al.
Publicado: (2024)

RAG-GFM: Overcoming In-Memory Bottlenecks in Graph Foundation Models via Retrieval-Augmented Generation
por: Yuan, Haonan, et al.
Publicado: (2026)

Parameterized Argumentation-based Reasoning Tasks for Benchmarking Generative Language Models
por: Steging, Cor, et al.
Publicado: (2025)

Three-dimensional attention Transformer for state evaluation in real-time strategy games
por: Ye, Yanqing, et al.
Publicado: (2025)

Low-Dimensional Execution Manifolds in Transformer Learning Dynamics: Evidence from Modular Arithmetic Tasks
por: Xu, Yongzhong
Publicado: (2026)

Provable In-Context Vector Arithmetic via Retrieving Task Concepts
por: Bu, Dake, et al.
Publicado: (2025)

Population Aware Diffusion for Time Series Generation
por: Li, Yang, et al.
Publicado: (2025)

Unveiling Memorization-Generalization Coexistence: A Case Study on Arithmetic Tasks with Label Noise
por: Liu, Linyu, et al.
Publicado: (2026)

Error-Driven Prompt Optimization for Arithmetic Reasoning
por: Pándy, Árpád, et al.
Publicado: (2025)

Balanced Direction from Multifarious Choices: Arithmetic Meta-Learning for Domain Generalization
por: Wang, Xiran, et al.
Publicado: (2025)

Quantifying and Understanding Uncertainty in Large Reasoning Models
por: Li, Yangyi, et al.
Publicado: (2026)

Unlocking Out-of-Distribution Generalization in Transformers via Recursive Latent Space Reasoning
por: Altabaa, Awni, et al.
Publicado: (2025)

Transformers Can Do Arithmetic with the Right Embeddings
por: McLeish, Sean, et al.
Publicado: (2024)

Beyond Reasoning Gains: Mitigating General Capabilities Forgetting in Large Reasoning Models
por: Phan, Hoang, et al.
Publicado: (2025)

Traj-Transformer: Diffusion Models with Transformer for GPS Trajectory Generation
por: Zhang, Zhiyang, et al.
Publicado: (2025)

Understanding the Training and Generalization of Pretrained Transformer for Sequential Decision Making
por: Wang, Hanzhao, et al.
Publicado: (2024)

Offline Reinforcement Learning with Generative Trajectory Policies
por: Feng, Xinsong, et al.
Publicado: (2025)

Efficient Embedding-based Synthetic Data Generation for Complex Reasoning Tasks
por: Jayaraman, Srideepika, et al.
Publicado: (2026)

Understanding Transformer Reasoning Capabilities via Graph Algorithms
por: Sanford, Clayton, et al.
Publicado: (2024)

Escaping Optimization Stagnation: Taking Steps Beyond Task Arithmetic via Difference Vectors
por: Wang, Jinping, et al.
Publicado: (2025)

Liquid Reasoning Transformers: A Sudoku-Based Prototype for Chess-Scale Algorithmic Tasks
por: Sahni, Shivansh, et al.
Publicado: (2025)

Towards Theoretical Understandings of Self-Consuming Generative Models
por: Fu, Shi, et al.
Publicado: (2024)

PAINET: A Principled Efficient Transformer for 3D Dynamics Modeling
por: Yang, Kai, et al.
Publicado: (2025)

CPL: Critical Plan Step Learning Boosts LLM Generalization in Reasoning Tasks
por: Wang, Tianlong, et al.
Publicado: (2024)

Understanding Tool-Integrated Reasoning
por: Lin, Heng, et al.
Publicado: (2025)

GSTM-HMU: Generative Spatio-Temporal Modeling for Human Mobility Understanding
por: Luo, Wenying, et al.
Publicado: (2025)

How Transformers Learn In-Context Recall Tasks? Optimality, Training Dynamics and Generalization
por: Nguyen, Quan, et al.
Publicado: (2025)

ReasoningWeekly: A General Knowledge and Verbal Reasoning Challenge for Large Language Models
por: Wu, Zixuan, et al.
Publicado: (2025)

Task Arithmetic in Trust Region: A Training-Free Model Merging Approach to Navigate Knowledge Conflicts
por: Sun, Wenju, et al.
Publicado: (2025)

When Reasoning Meets Compression: Understanding the Effects of LLMs Compression on Large Reasoning Models
por: Zhang, Nan, et al.
Publicado: (2025)

Integrating Arithmetic Learning Improves Mathematical Reasoning in Smaller Models
por: Gangwar, Neeraj, et al.
Publicado: (2025)

TimeOmni-VL: Unified Models for Time Series Understanding and Generation
por: Guan, Tong, et al.
Publicado: (2026)