Imagen de Portada

The Attribution Blind Spot: Detecting When Language Models Rely on Memory Rather Than Retrieved Context

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Yu, Zhe, Xing, Wenpeng, Wei, Yunzhao, Yang, Bo, Ye, Chen, Li, Gaolei, Han, Meng
Formato:	Preprint
Publicado:	2026
Materias:	Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

LatentAudit: Real-Time White-Box Faithfulness Monitoring for Retrieval-Augmented Generation with Verifiable Deployment
por: Yu, Zhe, et al.
Publicado: (2026)

Composition Collapse: Stable Factual Knowledge Does Not Imply Compositional Reasoning
por: Yu, Zhe, et al.
Publicado: (2026)

From Retinal Evidence to Safe Decisions: RETINA-SAFE and ECRT for Hallucination Risk Triage in Medical LLMs
por: Yu, Zhe, et al.
Publicado: (2026)

Cordon-MAS: Defending RAG against Knowledge Poisoning via Information-Flow Control
por: Yu, Zhe, et al.
Publicado: (2026)

Anti‐Tumour Immunity Relies on Targeting Tissue Homeostasis Through Monocyte‐Driven Responses Rather Than Direct Tumour Cytotoxicity
por: Nicholas Koelsch, et al.
Publicado: (2025)

KinGuard: Hierarchical Kinship-Aware Fingerprinting to Defend Against Large Language Model Stealing
por: Xu, Zhenhua, et al.
Publicado: (2026)

Blinded by Generated Contexts: How Language Models Merge Generated and Retrieved Contexts When Knowledge Conflicts?
por: Tan, Hexiang, et al.
Publicado: (2024)

EverTracer: Hunting Stolen Large Language Models via Stealthy and Robust Probabilistic Fingerprint
por: Xu, Zhenhua, et al.
Publicado: (2025)

When Do Individuals Believe in Themselves Rather Than in Artificial Intelligence? Insights from Longitudinal Investigations in Corporate Credit‐Rating Contexts
por: Kyootai Lee, et al.
Publicado: (2025)

Why Is There I Rather Than It?
por: Kudelska, Marta
Publicado: (2022)

To Rely or Not to Rely? Evaluating Interventions for Appropriate Reliance on Large Language Models
por: Bo, Jessica Y., et al.
Publicado: (2024)

AI in the Clinical Radiology and Radiation Oncology Assessed Curricula: When Rather Than If
por: Daniel E. Roos, et al.
Publicado: (2025)

HGMF: A Hierarchical Gaussian Mixture Framework for Scalable Tool Invocation within the Model Context Protocol
por: Xing, Wenpeng, et al.
Publicado: (2025)

Why Is There Something Rather Than Nothing?
por: Karakülah, Bülent
Publicado: (2026)

Observing Interaction Rather Than Interfaces
por: Rivière, Guillaume
Publicado: (2025)

CoDe-NeRF: Neural Rendering via Dynamic Coefficient Decomposition
por: Xing, Wenpeng, et al.
Publicado: (2025)

TeacherLM: Teaching to Fish Rather Than Giving the Fish, Language Modeling Likewise
por: He, Nan, et al.
Publicado: (2023)

Learning about Learning Rather Than about Teaching.
por: Markless, Sharon
Publicado: (2002)

Social Equality Is Rather Threatening Than Normative to Authoritarians
por: Márton Hadarics, et al.
Publicado: (2025)

Linguistic Blind Spots of Large Language Models
por: Cheng, Jiali, et al.
Publicado: (2025)

Temporal Blind Spots in Large Language Models
por: Wallat, Jonas, et al.
Publicado: (2024)

NeuRel-Attack: Neuron Relearning for Safety Disalignment in Large Language Models
por: Zhou, Yi, et al.
Publicado: (2025)

Blind OFDM-ISAC Relying on Asymmetric Modem Constellations
por: Pu, Henglin, et al.
Publicado: (2026)

Incorporating Rather Than Eliminating: Achieving Fairness for Skin Disease Diagnosis Through Group-Specific Expert
por: Xu, Gelei, et al.
Publicado: (2025)

Structured Memory Mechanisms for Stable Context Representation in Large Language Models
por: Xing, Yue, et al.
Publicado: (2025)

With Argus Eyes: Assessing Retrieval Gaps via Uncertainty Scoring to Detect and Remedy Retrieval Blind Spots
por: Taghavi, Zeinab Sadat, et al.
Publicado: (2026)

Simple Linguistic Inferences of Large Language Models (LLMs): Blind Spots and Blinds
por: Basmov, Victoria, et al.
Publicado: (2023)

Fluent but Unfeeling: The Emotional Blind Spots of Language Models
por: Shu, Bangzhao, et al.
Publicado: (2025)

PREE: Towards Harmless and Adaptive Fingerprint Editing in Large Language Models via Knowledge Prefix Enhancement
por: Yue, Xubin, et al.
Publicado: (2025)

Blind Spot Navigation in Large Language Model Reasoning with Thought Space Explorer
por: Zhang, Jinghan, et al.
Publicado: (2024)

Effects of Statistical Learning on Stimulus Detection Speed Reflect Attention Rather Than Representational Changes
por: Yoel Sheinenson, et al.
Publicado: (2026)

Blind Spots
por: Drucker, Johanna
Publicado: (2009)

Blind Spot Navigation: Evolutionary Discovery of Sensitive Semantic Concepts for LVLMs
por: Pan, Zihao, et al.
Publicado: (2025)

Selective Annotation via Data Allocation: These Data Should Be Triaged to Experts for Annotation Rather Than the Model
por: Huang, Chen, et al.
Publicado: (2024)

WhenLoss: Diagnosing Write and Retrieval Bottlenecks in Long-Context Memory Systems
por: Yu, Jiangnan, et al.
Publicado: (2026)

Illuminating Blind Spots of Language Models with Targeted Agent-in-the-Loop Synthetic Data
por: Lippmann, Philip, et al.
Publicado: (2024)

Memory-Augmented Large Language Models: External Memory, Retrieval Mechanisms, and Long-Context Processing
por: Junjie, Yang
Publicado: (2026)

Verification Blind Spots: When Branchless Code Defeats Static Analysis
por: Musselman, Blake
Publicado: (2026)

Incentivize Early Renewals Rather Than Train Members to Pay Late
Publicado: (2024)

SproutBench: A Benchmark for Safe and Ethical Large Language Models for Youth
por: Xing, Wenpeng, et al.
Publicado: (2025)