Copertina

When Do Hallucinations Arise? A Graph Perspective on the Evolution of Path Reuse and Path Compression

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Dai, Xinnan, Yang, Kai, Luo, Cheng, Zeng, Shenglai, Guo, Kai, Tang, Jiliang
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

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

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

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

Empowering GraphRAG with Knowledge Filtering and Integration
di: Guo, Kai, et al.
Pubblicazione: (2025)

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

From Sequence to Structure: Uncovering Substructure Reasoning in Transformers
di: Dai, Xinnan, et al.
Pubblicazione: (2025)

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

Unveiling Mode Connectivity in Graph Neural Networks
di: Li, Bingheng, et al.
Pubblicazione: (2025)

How Do Large Language Models Understand Graph Patterns? A Benchmark for Graph Pattern Comprehension
di: Dai, Xinnan, et al.
Pubblicazione: (2024)

Cumulative Path-Level Semantic Reasoning for Inductive Knowledge Graph Completion
di: Wang, Jiapu, et al.
Pubblicazione: (2026)

Fix Before Search: Benchmarking Agentic Query Visual Pre-processing in Multimodal Retrieval-augmented Generation
di: Zhang, Jiankun, et al.
Pubblicazione: (2026)

Investigating Out-of-Distribution Generalization of GNNs: An Architecture Perspective
di: Guo, Kai, et al.
Pubblicazione: (2024)

Position: Agentic Evolution is the Path to Evolving LLMs
di: Lin, Minhua, et al.
Pubblicazione: (2026)

PathRAG: Pruning Graph-based Retrieval Augmented Generation with Relational Paths
di: Chen, Boyu, et al.
Pubblicazione: (2025)

Query-Enhanced Adaptive Semantic Path Reasoning for Inductive Knowledge Graph Completion
di: Sun, Kai, et al.
Pubblicazione: (2024)

Unveiling Privacy Risks in LLM Agent Memory
di: Wang, Bo, et al.
Pubblicazione: (2025)

Enhancing Logical Expressiveness in Graph Neural Networks via Path-Neighbor Aggregation
di: Yu, Han, et al.
Pubblicazione: (2025)

HELP: HyperNode Expansion and Logical Path-Guided Evidence Localization for Accurate and Efficient GraphRAG
di: Huang, Yuqi, et al.
Pubblicazione: (2026)

Learning on Graphs with Large Language Models(LLMs): A Deep Dive into Model Robustness
di: Guo, Kai, et al.
Pubblicazione: (2024)

On the Evolution of Knowledge Graphs: A Survey and Perspective
di: Jiang, Xuhui, et al.
Pubblicazione: (2023)

MM-Path: Multi-modal, Multi-granularity Path Representation Learning -- Extended Version
di: Xu, Ronghui, et al.
Pubblicazione: (2024)

LLM-A*: Large Language Model Enhanced Incremental Heuristic Search on Path Planning
di: Meng, Silin, et al.
Pubblicazione: (2024)

KnowPath: Knowledge-enhanced Reasoning via LLM-generated Inference Paths over Knowledge Graphs
di: Zhao, Qi, et al.
Pubblicazione: (2025)

PathISE: Learning Informative Path Supervision for Knowledge Graph Question Answering
di: Gao, Shengxiang, et al.
Pubblicazione: (2026)

Pseudo-Knowledge Graph: Meta-Path Guided Retrieval and In-Graph Text for RAG-Equipped LLM
di: Yang, Yuxin, et al.
Pubblicazione: (2025)

Large-Scale Multirobot Coverage Path Planning on Grids With Path Deconfliction
di: Tang, Jingtao, et al.
Pubblicazione: (2024)

Mitigating Hallucinations in Large Language Models Via Decoder Layer Skipping
di: Li, Hanze, et al.
Pubblicazione: (2026)

Look Globally and Reason: Two-stage Path Reasoning over Sparse Knowledge Graphs
di: Guan, Saiping, et al.
Pubblicazione: (2024)

When Alignment Isn't Enough: Response-Path Attacks on LLM Agents
di: Luo, Mingyu, et al.
Pubblicazione: (2026)

Intervene-All-Paths: Unified Mitigation of LVLM Hallucinations across Alignment Formats
di: Qian, Jiaye, et al.
Pubblicazione: (2025)

When Agents Break Down in Multiagent Path Finding
di: Fioravantes, Foivos, et al.
Pubblicazione: (2025)

Neuro-Symbolic Agents for Hallucination-Free Requirements Reuse
di: Ibrahim, Ahmed F.
Pubblicazione: (2026)

Communication-Efficient Diffusion Denoising Parallelization via Reuse-then-Predict Mechanism
di: Wang, Kunyun, et al.
Pubblicazione: (2025)

PathE: Leveraging Entity-Agnostic Paths for Parameter-Efficient Knowledge Graph Embeddings
di: Reklos, Ioannis, et al.
Pubblicazione: (2025)

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

Skill Reuse as Compression in Agentic RL
di: Xu, Zhikun, et al.
Pubblicazione: (2026)

Do Language Models Know When They're Hallucinating References?
di: Agrawal, Ayush, et al.
Pubblicazione: (2023)

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

Intelligent Singularity Avoidance in UR10 Robotic Arm Path Planning Using Hybrid Fuzzy Logic and Reinforcement Learning
di: Chen, Sheng-Kai, et al.
Pubblicazione: (2026)

One Model for One Graph: A New Perspective for Pretraining with Cross-domain Graphs
di: Liu, Jingzhe, et al.
Pubblicazione: (2024)