Copertina

Complexity Control Facilitates Reasoning-Based Compositional Generalization in Transformers

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Zhang, Zhongwang, Lin, Pengxiao, Wang, Zhiwei, Zhang, Yaoyu, Xu, Zhi-Qin John
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computation and Language Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Reasoning Bias of Next Token Prediction Training
di: Lin, Pengxiao, et al.
Pubblicazione: (2025)

Initialization is Critical to Whether Transformers Fit Composite Functions by Reasoning or Memorizing
di: Zhang, Zhongwang, et al.
Pubblicazione: (2024)

An Analysis for Reasoning Bias of Language Models with Small Initialization
di: Yao, Junjie, et al.
Pubblicazione: (2025)

Scalable Complexity Control Facilitates Reasoning Ability of LLMs
di: Hang, Liangkai, et al.
Pubblicazione: (2025)

Understanding the Language Model to Solve the Symbolic Multi-Step Reasoning Problem from the Perspective of Buffer Mechanism
di: Wang, Zhiwei, et al.
Pubblicazione: (2024)

Anchor function: a type of benchmark functions for studying language models
di: Zhang, Zhongwang, et al.
Pubblicazione: (2024)

Local Linear Recovery Guarantee of Deep Neural Networks at Overparameterization
di: Zhang, Yaoyu, et al.
Pubblicazione: (2024)

Achilles' Heel of Mamba: Essential difficulties of the Mamba architecture demonstrated by synthetic data
di: Chen, Tianyi, et al.
Pubblicazione: (2025)

Identity Bridge: Enabling Implicit Reasoning via Shared Latent Memory
di: Lin, Pengxiao, et al.
Pubblicazione: (2025)

Loss Jump During Loss Switch in Solving PDEs with Neural Networks
di: Wang, Zhiwei, et al.
Pubblicazione: (2024)

A rationale from frequency perspective for grokking in training neural network
di: Zhou, Zhangchen, et al.
Pubblicazione: (2024)

ComplexFormer: Disruptively Advancing Transformer Inference Ability via Head-Specific Complex Vector Attention
di: Shao, Jintian, et al.
Pubblicazione: (2025)

Loss Spike in Training Neural Networks
di: Li, Xiaolong, et al.
Pubblicazione: (2023)

Embedding Principle in Depth for the Loss Landscape Analysis of Deep Neural Networks
di: Bai, Zhiwei, et al.
Pubblicazione: (2022)

Feature Resemblance: Towards a Theoretical Understanding of Analogical Reasoning in Transformers
di: Xu, Ruichen, et al.
Pubblicazione: (2026)

Generative Evaluation of Complex Reasoning in Large Language Models
di: Lin, Haowei, et al.
Pubblicazione: (2025)

Concept Algebra for (Score-Based) Text-Controlled Generative Models
di: Wang, Zihao, et al.
Pubblicazione: (2023)

Compositional Reasoning with Transformers, RNNs, and Chain of Thought
di: Yehudai, Gilad, et al.
Pubblicazione: (2025)

Self-Infilling Code Generation
di: Zheng, Lin, et al.
Pubblicazione: (2023)

Generalization or Hallucination? Understanding Out-of-Context Reasoning in Transformers
di: Huang, Yixiao, et al.
Pubblicazione: (2025)

XFinBench: Benchmarking LLMs in Complex Financial Problem Solving and Reasoning
di: Zhang, Zhihan, et al.
Pubblicazione: (2025)

Focus and Dilution: The Multi-stage Learning Process of Attention
di: Chen, Zheng-An, et al.
Pubblicazione: (2026)

A Complexity-Based Theory of Compositionality
di: Elmoznino, Eric, et al.
Pubblicazione: (2024)

Beyond Autoregression: Discrete Diffusion for Complex Reasoning and Planning
di: Ye, Jiacheng, et al.
Pubblicazione: (2024)

Complex Logical Instruction Generation
di: Zhang, Mian, et al.
Pubblicazione: (2025)

Circuit Compositions: Exploring Modular Structures in Transformer-Based Language Models
di: Mondorf, Philipp, et al.
Pubblicazione: (2024)

Reinforcing General Reasoning without Verifiers
di: Zhou, Xiangxin, et al.
Pubblicazione: (2025)

Light-IF: Endowing LLMs with Generalizable Reasoning via Preview and Self-Checking for Complex Instruction Following
di: Wang, Chenyang, et al.
Pubblicazione: (2025)

Retrieval-Reasoning Large Language Model-based Synthetic Clinical Trial Generation
di: Xu, Zerui, et al.
Pubblicazione: (2024)

Weights to Code: Extracting Interpretable Algorithms from the Discrete Transformer
di: Zhang, Yifan, et al.
Pubblicazione: (2026)

TRACE Back from the Future: A Probabilistic Reasoning Approach to Controllable Language Generation
di: Weng, Gwen Yidou, et al.
Pubblicazione: (2025)

Reasoning in Transformers -- Mitigating Spurious Correlations and Reasoning Shortcuts
di: Enström, Daniel, et al.
Pubblicazione: (2024)

Gained in Translation: Privileged Pairwise Judges Enhance Multilingual Reasoning
di: Sutawika, Lintang, et al.
Pubblicazione: (2026)

Interpreting and Controlling LLM Reasoning through Integrated Policy Gradient
di: Li, Changming, et al.
Pubblicazione: (2026)

On the Query Complexity of Verifier-Assisted Language Generation
di: Botta, Edoardo, et al.
Pubblicazione: (2025)

Benchmarking and Understanding Compositional Relational Reasoning of LLMs
di: Ni, Ruikang, et al.
Pubblicazione: (2024)

An overview of condensation phenomenon in deep learning
di: Xu, Zhi-Qin John, et al.
Pubblicazione: (2025)

Overview frequency principle/spectral bias in deep learning
di: Xu, Zhi-Qin John, et al.
Pubblicazione: (2022)

Laying the Foundation First? Investigating the Generalization from Atomic Skills to Complex Reasoning Tasks
di: Huang, Yuncheng, et al.
Pubblicazione: (2024)

Transformers meet Neural Algorithmic Reasoners
di: Bounsi, Wilfried, et al.
Pubblicazione: (2024)