Copertina

Attention Mechanisms Perspective: Exploring LLM Processing of Graph-Structured Data

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Guan, Zhong, Wu, Likang, Zhao, Hongke, He, Ming, Fan, Jianpin
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Artificial Intelligence Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

LangTopo: Aligning Language Descriptions of Graphs with Tokenized Topological Modeling
di: Guan, Zhong, et al.
Pubblicazione: (2024)

Enhancing Collaborative Semantics of Language Model-Driven Recommendations via Graph-Aware Learning
di: Guan, Zhong, et al.
Pubblicazione: (2024)

Recall-Extend Dynamics: Enhancing Small Language Models through Controlled Exploration and Refined Offline Integration
di: Guan, Zhong, et al.
Pubblicazione: (2025)

Multi-View Empowered Structural Graph Wordification for Language Models
di: Liu, Zipeng, et al.
Pubblicazione: (2024)

Round Attention: A Novel Round-Level Attention Mechanism to Accelerate LLM Inference
di: Tang, Yaohua, et al.
Pubblicazione: (2025)

D$^3$: Dynamic Directional Graph-Constrained Data Scheduling for LLM Training
di: Xu, Yuanjian, et al.
Pubblicazione: (2026)

Unifying Structured Data as Graph for Data-to-Text Pre-Training
di: Li, Shujie, et al.
Pubblicazione: (2024)

MGSA: Multi-Granularity Graph Structure Attention for Knowledge Graph-to-Text Generation
di: Wang, Shanshan, et al.
Pubblicazione: (2024)

LANID: LLM-assisted New Intent Discovery
di: Fan, Lu, et al.
Pubblicazione: (2025)

Table as Thought: Exploring Structured Thoughts in LLM Reasoning
di: Sun, Zhenjie, et al.
Pubblicazione: (2025)

Attention Needs to Focus: A Unified Perspective on Attention Allocation
di: Fu, Zichuan, et al.
Pubblicazione: (2026)

MinerU-Popo: Universal Post-Processing Model for Structured Document Parsing
di: Xu, Bangrui, et al.
Pubblicazione: (2026)

Incorporating Graph Attention Mechanism into Geometric Problem Solving Based on Deep Reinforcement Learning
di: Zhong, Xiuqin, et al.
Pubblicazione: (2024)

SAKE: Structured Agentic Knowledge Extrapolation for Complex LLM Reasoning via Reinforcement Learning
di: He, Jiashu, et al.
Pubblicazione: (2025)

Advanced Unstructured Data Processing for ESG Reports: A Methodology for Structured Transformation and Enhanced Analysis
di: Peng, Jiahui, et al.
Pubblicazione: (2024)

Generate-on-Graph: Treat LLM as both Agent and KG in Incomplete Knowledge Graph Question Answering
di: Xu, Yao, et al.
Pubblicazione: (2024)

GIVE: Structured Reasoning of Large Language Models with Knowledge Graph Inspired Veracity Extrapolation
di: He, Jiashu, et al.
Pubblicazione: (2024)

IMAGINE: Integrating Multi-Agent System into One Model for Complex Reasoning and Planning
di: Zhang, Xikai, et al.
Pubblicazione: (2025)

Seeking Neural Nuggets: Knowledge Transfer in Large Language Models from a Parametric Perspective
di: Zhong, Ming, et al.
Pubblicazione: (2023)

Multi-dimensional Data Analysis and Applications Basing on LLM Agents and Knowledge Graph Interactions
di: Wang, Xi, et al.
Pubblicazione: (2025)

ConvD: Attention Enhanced Dynamic Convolutional Embeddings for Knowledge Graph Completion
di: Guo, Wenbin, et al.
Pubblicazione: (2023)

Structured Attention Matters to Multimodal LLMs in Document Understanding
di: Liu, Chang, et al.
Pubblicazione: (2025)

GuideLLM: Exploring LLM-Guided Conversation with Applications in Autobiography Interviewing
di: Duan, Jinhao, et al.
Pubblicazione: (2025)

AGENTiGraph: A Multi-Agent Knowledge Graph Framework for Interactive, Domain-Specific LLM Chatbots
di: Zhao, Xinjie, et al.
Pubblicazione: (2025)

Deep Learning Based Dense Retrieval: A Comparative Study
di: Zhong, Ming, et al.
Pubblicazione: (2024)

Exploring Knowledge Conflicts for Faithful LLM Reasoning: Benchmark and Method
di: Zhao, Tianzhe, et al.
Pubblicazione: (2026)

Advancements in Natural Language Processing: Exploring Transformer-Based Architectures for Text Understanding
di: Wu, Tianhao, et al.
Pubblicazione: (2025)

Perspective Dial: Measuring Perspective of Text and Guiding LLM Outputs
di: Kim, Taejin, et al.
Pubblicazione: (2025)

SWAA: Sliding Window Attention Adaptation for Efficient and Quality Preserving Long Context Processing
di: Yu, Yijiong, et al.
Pubblicazione: (2025)

From Similarity to Structure: Training-free LLM Context Compression with Hybrid Graph Priors
di: Zhou, Yitian, et al.
Pubblicazione: (2026)

Efficient Data Learning for Open Information Extraction with Pre-trained Language Models
di: Fan, Zhiyuan, et al.
Pubblicazione: (2023)

Exploring the Necessity of Reasoning in LLM-based Agent Scenarios
di: Zhou, Xueyang, et al.
Pubblicazione: (2025)

Who is Undercover? Guiding LLMs to Explore Multi-Perspective Team Tactic in the Game
di: Dong, Ruiqi, et al.
Pubblicazione: (2024)

Distil-xLSTM: Learning Attention Mechanisms through Recurrent Structures
di: Thiombiano, Abdoul Majid O., et al.
Pubblicazione: (2025)

Missing Old Logits in Asynchronous Agentic RL: Semantic Mismatch and Repair Methods for Off-Policy Correction
di: Guan, Zhong, et al.
Pubblicazione: (2026)

Self-Describing Structured Data with Dual-Layer Guidance: A Lightweight Alternative to RAG for Precision Retrieval in Large-Scale LLM Knowledge Navigation
di: Liu, Hung Ming
Pubblicazione: (2026)

SampleAttention: Near-Lossless Acceleration of Long Context LLM Inference with Adaptive Structured Sparse Attention
di: Zhu, Qianchao, et al.
Pubblicazione: (2024)

Understanding the Thinking Process of Reasoning Models: A Perspective from Schoenfeld's Episode Theory
di: Li, Ming, et al.
Pubblicazione: (2025)

Why Reinforcement Fine-Tuning Enables MLLMs Preserve Prior Knowledge Better: A Data Perspective
di: Zhang, Zhihao, et al.
Pubblicazione: (2025)

Middo: Model-Informed Dynamic Data Optimization for Enhanced LLM Fine-Tuning via Closed-Loop Learning
di: Tang, Zinan, et al.
Pubblicazione: (2025)