Imagen de Portada

Beyond Context: Large Language Models' Failure to Grasp Users' Intent

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Hussain, Ahmed M., Salahuddin, Salahuddin
Formato:	Preprint
Publicado:	2025
Materias:	Artificial Intelligence Computation and Language Cryptography and Security Computers and Society
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Less Data, More Security: Advancing Cybersecurity LLMs Specialization via Resource-Efficient Domain-Adaptive Continuous Pre-training with Minimal Tokens
por: Salahuddin, Salahuddin, et al.
Publicado: (2025)

RealHarm: A Collection of Real-World Language Model Application Failures
por: Jeune, Pierre Le, et al.
Publicado: (2025)

Jailbreaking Large Language Models Through Content Concretization
por: Wahréus, Johan, et al.
Publicado: (2025)

Phare: A Safety Probe for Large Language Models
por: Jeune, Pierre Le, et al.
Publicado: (2025)

Attacks on Third-Party APIs of Large Language Models
por: Zhao, Wanru, et al.
Publicado: (2024)

TombRaider: Entering the Vault of History to Jailbreak Large Language Models
por: Ding, Junchen, et al.
Publicado: (2025)

Bridging the Copyright Gap: Do Large Vision-Language Models Recognize and Respect Copyrighted Content?
por: Xu, Naen, et al.
Publicado: (2025)

Can LLMs Infer Conversational Agent Users' Personality Traits from Chat History?
por: Cögendez, Derya, et al.
Publicado: (2026)

User Privacy and Large Language Models: An Analysis of Frontier Developers' Privacy Policies
por: King, Jennifer, et al.
Publicado: (2025)

Medical Malice: A Dataset for Context-Aware Safety in Healthcare LLMs
por: D'addario, Andrew Maranhão Ventura
Publicado: (2025)

How Well Can LLM Agents Simulate End-User Security and Privacy Attitudes and Behaviors?
por: Li, Yuxuan, et al.
Publicado: (2026)

CCJA: Context-Coherent Jailbreak Attack for Aligned Large Language Models
por: Zhou, Guanghao, et al.
Publicado: (2025)

Advancing Beyond Identification: Multi-bit Watermark for Large Language Models
por: Yoo, KiYoon, et al.
Publicado: (2023)

GPT, Ontology, and CAABAC: A Tripartite Personalized Access Control Model Anchored by Compliance, Context and Attribute
por: Nowrozy, Raza, et al.
Publicado: (2024)

Leveraging Large Language Models for Preliminary Security Risk Analysis: A Mission-Critical Case Study
por: Esposito, Matteo, et al.
Publicado: (2024)

RedAgent: Red Teaming Large Language Models with Context-aware Autonomous Language Agent
por: Xu, Huiyu, et al.
Publicado: (2024)

Jailbreak-Tuning: Models Efficiently Learn Jailbreak Susceptibility
por: Murphy, Brendan, et al.
Publicado: (2025)

Character as a Latent Variable in Large Language Models: A Mechanistic Account of Emergent Misalignment and Conditional Safety Failures
por: Su, Yanghao, et al.
Publicado: (2026)

Watermarking Language Models for Many Adaptive Users
por: Cohen, Aloni, et al.
Publicado: (2024)

Building Intelligence Identification System via Large Language Model Watermarking: A Survey and Beyond
por: Wang, Xuhong, et al.
Publicado: (2024)

LLMs Have Rhythm: Fingerprinting Large Language Models Using Inter-Token Times and Network Traffic Analysis
por: Alhazbi, Saeif, et al.
Publicado: (2025)

CATMark: A Context-Aware Thresholding Framework for Robust Cross-Task Watermarking in Large Language Models
por: Zhang, Yu, et al.
Publicado: (2025)

Auditing Pay-Per-Token in Large Language Models
por: Velasco, Ander Artola, et al.
Publicado: (2025)

Cybench: A Framework for Evaluating Cybersecurity Capabilities and Risks of Language Models
por: Zhang, Andy K., et al.
Publicado: (2024)

A Longitudinal Measurement of Privacy Policy Evolution for Large Language Models
por: Tao, Zhen, et al.
Publicado: (2025)

A Survey on Responsible LLMs: Inherent Risk, Malicious Use, and Mitigation Strategy
por: Wang, Huandong, et al.
Publicado: (2025)

Nuclear Deployed: Analyzing Catastrophic Risks in Decision-making of Autonomous LLM Agents
por: Xu, Rongwu, et al.
Publicado: (2025)

Complete Evasion, Zero Modification: PDF Attacks on AI Text Detection
por: Creo, Aldan
Publicado: (2025)

Blueprints of Trust: AI System Cards for End to End Transparency and Governance
por: Sidhpurwala, Huzaifa, et al.
Publicado: (2025)

Children's Voice Privacy: First Steps And Emerging Challenges
por: Kulkarni, Ajinkya, et al.
Publicado: (2025)

AuditGPT: Auditing Smart Contracts with ChatGPT
por: Xia, Shihao, et al.
Publicado: (2024)

How Alignment and Jailbreak Work: Explain LLM Safety through Intermediate Hidden States
por: Zhou, Zhenhong, et al.
Publicado: (2024)

SWAN: Semantic Watermarking with Abstract Meaning Representation
por: Ye, Ziping, et al.
Publicado: (2026)

ROK-FORTRESS: Measuring the Effect of Geopolitical Transcreation for National Security and Public Safety
por: Lee, Michael S., et al.
Publicado: (2026)

The Earth is Flat because...: Investigating LLMs' Belief towards Misinformation via Persuasive Conversation
por: Xu, Rongwu, et al.
Publicado: (2023)

Assessing LLM Response Quality in the Context of Technology-Facilitated Abuse
por: Prakash, Vijay, et al.
Publicado: (2026)

Playing Devil's Advocate: Unmasking Toxicity and Vulnerabilities in Large Vision-Language Models
por: Erol, Abdulkadir, et al.
Publicado: (2025)

Guardrails for trust, safety, and ethical development and deployment of Large Language Models (LLM)
por: Biswas, Anjanava, et al.
Publicado: (2026)

A Proposal for Evaluating the Operational Risk for ChatBots based on Large Language Models
por: Pinacho-Davidson, Pedro, et al.
Publicado: (2025)

BEACON: A Unified Behavioral-Tactical Framework for Explainable Cybercrime Analysis with Large Language Models
por: Sachdeva, Arush, et al.
Publicado: (2025)