Cover Image

Are Transformers Able to Reason by Connecting Separated Knowledge in Training Data?

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Yin, Yutong, Wang, Zhaoran
Format:	Preprint
Published:	2025
Subjects:	Artificial Intelligence Computation and Language Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Learning to Reason as Action Abstractions with Scalable Mid-Training RL
by: Zhang, Shenao, et al.
Published: (2025)

BRiTE: Bootstrapping Reinforced Thinking Process to Enhance Language Model Reasoning
by: Zhong, Han, et al.
Published: (2025)

Beyond Markovian: Reflective Exploration via Bayes-Adaptive RL for LLM Reasoning
by: Zhang, Shenao, et al.
Published: (2025)

Teaching Transformers Causal Reasoning through Axiomatic Training
by: Vashishtha, Aniket, et al.
Published: (2024)

Can Post-Training Transform LLMs into Causal Reasoners?
by: Chen, Junqi, et al.
Published: (2026)

KDRL: Post-Training Reasoning LLMs via Unified Knowledge Distillation and Reinforcement Learning
by: Xu, Hongling, et al.
Published: (2025)

Decoupling Knowledge and Reasoning in Transformers: A Modular Architecture with Generalized Cross-Attention
by: Guo, Zhenyu, et al.
Published: (2025)

A Dual-View Approach to Classifying Radiology Reports by Co-Training
by: Han, Yutong, et al.
Published: (2024)

StepFun-Formalizer: Unlocking the Autoformalization Potential of LLMs through Knowledge-Reasoning Fusion
by: Wu, Yutong, et al.
Published: (2025)

Connecting the Dots: LLMs can Infer and Verbalize Latent Structure from Disparate Training Data
by: Treutlein, Johannes, et al.
Published: (2024)

AdaSTaR: Adaptive Data Sampling for Training Self-Taught Reasoners
by: Koh, Woosung, et al.
Published: (2025)

STAT: Shrinking Transformers After Training
by: Flynn, Megan, et al.
Published: (2024)

MedAgentGym: A Scalable Agentic Training Environment for Code-Centric Reasoning in Biomedical Data Science
by: Xu, Ran, et al.
Published: (2025)

Knowledge Graph Reasoning with Self-supervised Reinforcement Learning
by: Ma, Ying, et al.
Published: (2024)

How Instruction and Reasoning Data shape Post-Training: Data Quality through the Lens of Layer-wise Gradients
by: Li, Ming, et al.
Published: (2025)

Parallax: Parameterized Local Linear Attention for Language Modeling
by: Zuo, Yifei, et al.
Published: (2026)

Layerwise Change of Knowledge in Neural Networks
by: Cheng, Xu, et al.
Published: (2024)

Counterfactual Reasoning with Knowledge Graph Embeddings
by: Zellinger, Lena, et al.
Published: (2024)

Power Transformer Fault Prediction Based on Knowledge Graphs
by: Wang, Chao, et al.
Published: (2024)

SymAgent: A Neural-Symbolic Self-Learning Agent Framework for Complex Reasoning over Knowledge Graphs
by: Liu, Ben, et al.
Published: (2025)

Learning to Detect Language Model Training Data via Active Reconstruction
by: Yin, Junjie Oscar, et al.
Published: (2026)

Logical Structure as Knowledge: Enhancing LLM Reasoning via Structured Logical Knowledge Density Estimation
by: Bi, Zhen, et al.
Published: (2025)

Training Large Language Models To Reason In Parallel With Global Forking Tokens
by: Jia, Sheng, et al.
Published: (2025)

MegaScience: Pushing the Frontiers of Post-Training Datasets for Science Reasoning
by: Fan, Run-Ze, et al.
Published: (2025)

Solo Connection: A Parameter Efficient Fine-Tuning Technique for Transformers
by: Pathak, Harsh Nilesh, et al.
Published: (2025)

Reinforcement Learning for Reasoning in Large Language Models with One Training Example
by: Wang, Yiping, et al.
Published: (2025)

SpanNorm: Reconciling Training Stability and Performance in Deep Transformers
by: Wang, Chao, et al.
Published: (2026)

Transformer-Based Multimodal Knowledge Graph Completion with Link-Aware Contexts
by: Ma, Haodi, et al.
Published: (2025)

Examining Reasoning LLMs-as-Judges in Non-Verifiable LLM Post-Training
by: Liu, Yixin, et al.
Published: (2026)

On Designing Effective RL Reward at Training Time for LLM Reasoning
by: Gao, Jiaxuan, et al.
Published: (2024)

Learning to Reason Efficiently with A* Post-Training
by: Opedal, Andreas, et al.
Published: (2026)

Learning from Synthetic Data Improves Multi-hop Reasoning
by: Kabra, Anmol, et al.
Published: (2026)

MUDDFormer: Breaking Residual Bottlenecks in Transformers via Multiway Dynamic Dense Connections
by: Xiao, Da, et al.
Published: (2025)

Memorization vs. Reasoning: Updating LLMs with New Knowledge
by: Li, Aochong Oliver, et al.
Published: (2025)

Compute Optimal Scaling of Skills: Knowledge vs Reasoning
by: Roberts, Nicholas, et al.
Published: (2025)

Reasoning with Latent Thoughts: On the Power of Looped Transformers
by: Saunshi, Nikunj, et al.
Published: (2025)

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

SenTSR-Bench: Thinking with Injected Knowledge for Time-Series Reasoning
by: He, Zelin, et al.
Published: (2026)

Mid-Think: Training-Free Intermediate-Budget Reasoning via Token-Level Triggers
by: Yang, Wang, et al.
Published: (2026)

How to Train Data-Efficient LLMs
by: Sachdeva, Noveen, et al.
Published: (2024)