Cover Image

From Sequence to Structure: Uncovering Substructure Reasoning in Transformers

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Dai, Xinnan, Yang, Kai, Revolinsky, Jay, Guo, Kai, Wang, Aoran, Zhang, Bohang, Tang, Jiliang
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Uncovering Graph Reasoning in Decoder-only Transformers with Circuit Tracing
by: Dai, Xinnan, et al.
Published: (2025)

Why Retrieval-Augmented Generation Fails: A Graph Perspective
by: Guo, Kai, et al.
Published: (2026)

Revisiting the Graph Reasoning Ability of Large Language Models: Case Studies in Translation, Connectivity and Shortest Path
by: Dai, Xinnan, et al.
Published: (2024)

Subgraph Generation for Generalizing on Out-of-Distribution Links
by: Revolinsky, Jay, et al.
Published: (2025)

Towards Understanding Link Predictor Generalizability Under Distribution Shifts
by: Revolinsky, Jay, et al.
Published: (2024)

Towards Better Benchmark Datasets for Inductive Knowledge Graph Completion
by: Shomer, Harry, et al.
Published: (2024)

Are Expressive Encoders Necessary for Discrete Graph Generation?
by: Revolinsky, Jay, et al.
Published: (2026)

When Do Hallucinations Arise? A Graph Perspective on the Evolution of Path Reuse and Path Compression
by: Dai, Xinnan, et al.
Published: (2026)

Do Efficient Transformers Really Save Computation?
by: Yang, Kai, et al.
Published: (2024)

Evaluation of Retrieval-Augmented Generation: A Survey
by: Yu, Hao, et al.
Published: (2024)

Code-driven Number Sequence Calculation: Enhancing the inductive Reasoning Abilities of Large Language Models
by: Chen, Kedi, et al.
Published: (2025)

Enhancing Knowledge Graph Completion with Entity Neighborhood and Relation Context
by: Chen, Jianfang, et al.
Published: (2025)

Empowering Few-Shot Relation Extraction with The Integration of Traditional RE Methods and Large Language Models
by: Liu, Ye, et al.
Published: (2024)

Residual Connections and the Causal Shift: Uncovering a Structural Misalignment in Transformers
by: Lys, Jonathan, et al.
Published: (2026)

GraphGhost: Tracing Structures Behind Large Language Models
by: Dai, Xinnan, et al.
Published: (2025)

LLM-Driven Multi-Turn Task-Oriented Dialogue Synthesis for Realistic Reasoning
by: Zhu, Yu, et al.
Published: (2026)

From General Reasoning to Domain Expertise: Uncovering the Limits of Generalization in Large Language Models
by: Alsagheer, Dana, et al.
Published: (2025)

S3Mem: Structured Spatiotemporal Scene-Event Memory for Long-Horizon Interactive Question Answering
by: Su, Encheng, et al.
Published: (2026)

Markov Chain of Thought for Efficient Mathematical Reasoning
by: Yang, Wen, et al.
Published: (2024)

Beyond Static Retrieval: Opportunities and Pitfalls of Iterative Retrieval in GraphRAG
by: Guo, Kai, et al.
Published: (2025)

Forest-of-Thought: Scaling Test-Time Compute for Enhancing LLM Reasoning
by: Bi, Zhenni, et al.
Published: (2024)

What Really Improves Mathematical Reasoning: Structured Reasoning Signals Beyond Pure Code
by: Zhao, Yuze, et al.
Published: (2026)

LLM Factoscope: Uncovering LLMs' Factual Discernment through Inner States Analysis
by: He, Jinwen, et al.
Published: (2023)

Distilling the Essence: Efficient Reasoning Distillation via Sequence Truncation
by: Chen, Wei-Rui, et al.
Published: (2025)

Surgical Post-Training: Proximal On-Policy Distillation for Reasoning with Knowledge Retention
by: Lin, Wenye, et al.
Published: (2026)

From Conflict to Consensus: Boosting Medical Reasoning via Multi-Round Agentic RAG
by: Wu, Wenhao, et al.
Published: (2026)

Decoupling Understanding from Reasoning via Problem Space Mapping for Small-Scale Model Reasoning
by: Wang, Li, et al.
Published: (2025)

Sequence to Sequence Reward Modeling: Improving RLHF by Language Feedback
by: Zhou, Jiayi, et al.
Published: (2024)

Adaptive Test-Time Reasoning via Reward-Guided Dual-Phase Search
by: Cui, Yingqian, et al.
Published: (2025)

Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
by: Li, Hang, et al.
Published: (2025)

Structured Outputs Enable General-Purpose LLMs to be Medical Experts
by: Guo, Guangfu, et al.
Published: (2025)

Abstract2Appendix: Academic Reviews Enhance LLM Long-Context Capabilities
by: Li, Shengzhi, et al.
Published: (2024)

Exploring the Reversal Curse and Other Deductive Logical Reasoning in BERT and GPT-Based Large Language Models
by: Wu, Da, et al.
Published: (2023)

Knowledge Tagging System on Math Questions via LLMs with Flexible Demonstration Retriever
by: Li, Hang, et al.
Published: (2024)

A Theoretical Understanding of Chain-of-Thought: Coherent Reasoning and Error-Aware Demonstration
by: Cui, Yingqian, et al.
Published: (2024)

Kwai-STaR: Transform LLMs into State-Transition Reasoners
by: Lu, Xingyu, et al.
Published: (2024)

Matrix as Plan: Structured Logical Reasoning with Feedback-Driven Replanning
by: Chen, Ke, et al.
Published: (2026)

CHiSafetyBench: A Chinese Hierarchical Safety Benchmark for Large Language Models
by: Zhang, Wenjing, et al.
Published: (2024)

EndoCogniAgent: Closed-Loop Agentic Reasoning with Self-Consistency Validation for Endoscopic Diagnosis
by: Tang, Yi, et al.
Published: (2025)

ReCo: Reliable Causal Chain Reasoning via Structural Causal Recurrent Neural Networks
by: Xiong, Kai, et al.
Published: (2022)