Understanding the Language Model to Solve the Symbolic Multi-Step Reasoning Problem from the Perspective of Buffer Mechanism
Fuente:
arXiv
Saved in:
| Main Authors: | Wang, Zhiwei, Wang, Yunji, Zhang, Zhongwang, Zhou, Zhangchen, Jin, Hui, Hu, Tianyang, Sun, Jiacheng, Li, Zhenguo, Zhang, Yaoyu, Xu, Zhi-Qin John |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
Complexity Control Facilitates Reasoning-Based Compositional Generalization in Transformers
by: Zhang, Zhongwang, et al.
Published: (2025)
by: Zhang, Zhongwang, et al.
Published: (2025)
Initialization is Critical to Whether Transformers Fit Composite Functions by Reasoning or Memorizing
by: Zhang, Zhongwang, et al.
Published: (2024)
by: Zhang, Zhongwang, et al.
Published: (2024)
Loss Jump During Loss Switch in Solving PDEs with Neural Networks
by: Wang, Zhiwei, et al.
Published: (2024)
by: Wang, Zhiwei, et al.
Published: (2024)
Local Linear Recovery Guarantee of Deep Neural Networks at Overparameterization
by: Zhang, Yaoyu, et al.
Published: (2024)
by: Zhang, Yaoyu, et al.
Published: (2024)
A rationale from frequency perspective for grokking in training neural network
by: Zhou, Zhangchen, et al.
Published: (2024)
by: Zhou, Zhangchen, et al.
Published: (2024)
An overview of condensation phenomenon in deep learning
by: Xu, Zhi-Qin John, et al.
Published: (2025)
by: Xu, Zhi-Qin John, et al.
Published: (2025)
Anchor function: a type of benchmark functions for studying language models
by: Zhang, Zhongwang, et al.
Published: (2024)
by: Zhang, Zhongwang, et al.
Published: (2024)
Symbolic or Numerical? Understanding Physics Problem Solving in Reasoning LLMs
by: Dan, Nifu, et al.
Published: (2025)
by: Dan, Nifu, et al.
Published: (2025)
Reasoning Bias of Next Token Prediction Training
by: Lin, Pengxiao, et al.
Published: (2025)
by: Lin, Pengxiao, et al.
Published: (2025)
An Analysis for Reasoning Bias of Language Models with Small Initialization
by: Yao, Junjie, et al.
Published: (2025)
by: Yao, Junjie, et al.
Published: (2025)
Limit Analysis for Symbolic Multi-step Reasoning Tasks with Information Propagation Rules Based on Transformers
by: Qin, Tian, et al.
Published: (2025)
by: Qin, Tian, et al.
Published: (2025)
Adding Additional Control to One-Step Diffusion with Joint Distribution Matching
by: Luo, Yihong, et al.
Published: (2025)
by: Luo, Yihong, et al.
Published: (2025)
Scalable Complexity Control Facilitates Reasoning Ability of LLMs
by: Hang, Liangkai, et al.
Published: (2025)
by: Hang, Liangkai, et al.
Published: (2025)
Diff-Instruct: A Universal Approach for Transferring Knowledge From Pre-trained Diffusion Models
by: Luo, Weijian, et al.
Published: (2023)
by: Luo, Weijian, et al.
Published: (2023)
Adaptive Preconditioners Trigger Loss Spikes in Adam
by: Bai, Zhiwei, et al.
Published: (2025)
by: Bai, Zhiwei, et al.
Published: (2025)
G-LLaVA: Solving Geometric Problem with Multi-Modal Large Language Model
by: Gao, Jiahui, et al.
Published: (2023)
by: Gao, Jiahui, et al.
Published: (2023)
Embedding Principle in Depth for the Loss Landscape Analysis of Deep Neural Networks
by: Bai, Zhiwei, et al.
Published: (2022)
by: Bai, Zhiwei, et al.
Published: (2022)
Hilbert-Geo: Solving Solid Geometric Problems by Neural-Symbolic Reasoning
by: Xu, Ruoran, et al.
Published: (2026)
by: Xu, Ruoran, et al.
Published: (2026)
Accelerating Diffusion Sampling with Optimized Time Steps
by: Xue, Shuchen, et al.
Published: (2024)
by: Xue, Shuchen, et al.
Published: (2024)
Loss Spike in Training Neural Networks
by: Li, Xiaolong, et al.
Published: (2023)
by: Li, Xiaolong, et al.
Published: (2023)
Evaluating Step-by-Step Reasoning through Symbolic Verification
by: Zhang, Yi-Fan, et al.
Published: (2022)
by: Zhang, Yi-Fan, et al.
Published: (2022)
Solving multiscale dynamical systems by deep learning
by: Yao, Junjie, et al.
Published: (2024)
by: Yao, Junjie, et al.
Published: (2024)
MathMistake Checker: A Comprehensive Demonstration for Step-by-Step Math Problem Mistake Finding by Prompt-Guided LLMs
by: Zhang, Tianyang, et al.
Published: (2025)
by: Zhang, Tianyang, et al.
Published: (2025)
Learning Few-Step Diffusion Models by Trajectory Distribution Matching
by: Luo, Yihong, et al.
Published: (2025)
by: Luo, Yihong, et al.
Published: (2025)
Variational Autoencoding Discrete Diffusion with Enhanced Dimensional Correlations Modeling
by: Xie, Tianyu, et al.
Published: (2025)
by: Xie, Tianyu, et al.
Published: (2025)
A Survey of Deep Learning for Geometry Problem Solving
by: Ma, Jianzhe, et al.
Published: (2025)
by: Ma, Jianzhe, et al.
Published: (2025)
Connectivity Shapes Implicit Regularization in Matrix Factorization Models for Matrix Completion
by: Bai, Zhiwei, et al.
Published: (2024)
by: Bai, Zhiwei, et al.
Published: (2024)
Disentangle Sample Size and Initialization Effect on Perfect Generalization for Single-Neuron Target
by: Zhao, Jiajie, et al.
Published: (2024)
by: Zhao, Jiajie, et al.
Published: (2024)
FourierCSP: Differentiable Constraint Satisfaction Problem Solving by Walsh-Fourier Expansion
by: Cen, Yunuo, et al.
Published: (2025)
by: Cen, Yunuo, et al.
Published: (2025)
MA-GTS: A Multi-Agent Framework for Solving Complex Graph Problems in Real-World Applications
by: Yuan, Zike, et al.
Published: (2025)
by: Yuan, Zike, et al.
Published: (2025)
How Do LLMs Acquire New Knowledge? A Knowledge Circuits Perspective on Continual Pre-Training
by: Ou, Yixin, et al.
Published: (2025)
by: Ou, Yixin, et al.
Published: (2025)
SpatialMath: Spatial Comprehension-Infused Symbolic Reasoning for Mathematical Problem-Solving
by: Bajpai, Ashutosh, et al.
Published: (2026)
by: Bajpai, Ashutosh, et al.
Published: (2026)
Speak It Out: Solving Symbol-Related Problems with Symbol-to-Language Conversion for Language Models
by: Wang, Yile, et al.
Published: (2024)
by: Wang, Yile, et al.
Published: (2024)
GeoMathCode: Understanding Interleaved Math-Code Reasoning for Geometry Problem Solving
by: Zhang, Yingji, et al.
Published: (2026)
by: Zhang, Yingji, et al.
Published: (2026)
Overview frequency principle/spectral bias in deep learning
by: Xu, Zhi-Qin John, et al.
Published: (2022)
by: Xu, Zhi-Qin John, et al.
Published: (2022)
LLM Reasoners: New Evaluation, Library, and Analysis of Step-by-Step Reasoning with Large Language Models
by: Hao, Shibo, et al.
Published: (2024)
by: Hao, Shibo, et al.
Published: (2024)
Plane Geometry Problem Solving with Multi-modal Reasoning: A Survey
by: Cho, Seunghyuk, et al.
Published: (2025)
by: Cho, Seunghyuk, et al.
Published: (2025)
Any-Order GPT as Masked Diffusion Model: Decoupling Formulation and Architecture
by: Xue, Shuchen, et al.
Published: (2025)
by: Xue, Shuchen, et al.
Published: (2025)
Enhancing the Geometric Problem-Solving Ability of Multimodal LLMs via Symbolic-Neural Integration
by: Pan, Yicheng, et al.
Published: (2025)
by: Pan, Yicheng, et al.
Published: (2025)
Solving Poisson Problems in Polygonal Domains with Singularity Enriched Physics Informed Neural Networks
by: Hu, Tianhao, et al.
Published: (2023)
by: Hu, Tianhao, et al.
Published: (2023)
Similar Items
-
Complexity Control Facilitates Reasoning-Based Compositional Generalization in Transformers
by: Zhang, Zhongwang, et al.
Published: (2025) -
Initialization is Critical to Whether Transformers Fit Composite Functions by Reasoning or Memorizing
by: Zhang, Zhongwang, et al.
Published: (2024) -
Loss Jump During Loss Switch in Solving PDEs with Neural Networks
by: Wang, Zhiwei, et al.
Published: (2024) -
Local Linear Recovery Guarantee of Deep Neural Networks at Overparameterization
by: Zhang, Yaoyu, et al.
Published: (2024) -
A rationale from frequency perspective for grokking in training neural network
by: Zhou, Zhangchen, et al.
Published: (2024)