Imagen de Portada

Beyond Refusal: Probing the Limits of Agentic Self-Correction for Semantic Sensitive Information

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Suleymanov, Umid, Rajabov, Zaur, Mirzazada, Emil, Kantarcioglu, Murat
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

SIGMA: Search-Augmented On-Demand Knowledge Integration for Agentic Mathematical Reasoning
por: Asgarov, Ali, et al.
Publicado: (2025)

CourtGuard: A Model-Agnostic Framework for Zero-Shot Policy Adaptation in LLM Safety
por: Suleymanov, Umid, et al.
Publicado: (2026)

SPRINT: Semi-supervised Prototypical Representation for Few-Shot Class-Incremental Tabular Learning
por: Suleymanov, Umid, et al.
Publicado: (2026)

First, Do No Harm (With LLMs): Mitigating Racial Bias via Agentic Workflows
por: Xing, Sihao, et al.
Publicado: (2026)

Bypassing AI Control Protocols via Agent-as-a-Proxy Attacks
por: Isbarov, Jafar, et al.
Publicado: (2026)

PARALLAX: Separating Genuine Hallucination Detection from Benchmark Construction Artifacts
por: Hussain, Khizar, et al.
Publicado: (2026)

Refusal Steering: Fine-grained Control over LLM Refusal Behaviour for Sensitive Topics
por: García-Ferrero, Iker, et al.
Publicado: (2025)

A Revealed Preference Framework for AI Alignment
por: Suleymanov, Elchin
Publicado: (2026)

FedDAG: Clustered Federated Learning via Global Data and Gradient Integration for Heterogeneous Environments
por: Pramanik, Anik, et al.
Publicado: (2026)

Using AI Uncertainty Quantification to Improve Human Decision-Making
por: Marusich, Laura R., et al.
Publicado: (2023)

Beyond Shortest Path: Agentic Vehicular Routing with Semantic Context
por: Braun, Carnot, et al.
Publicado: (2025)

From Refusal Tokens to Refusal Control: Discovering and Steering Category-Specific Refusal Directions
por: Alagharu, Rishab, et al.
Publicado: (2026)

Blending Human and LLM Expertise to Detect Hallucinations and Omissions in Mental Health Chatbot Responses
por: Hussain, Khizar, et al.
Publicado: (2026)

Learn to Refuse: Making Large Language Models More Controllable and Reliable through Knowledge Scope Limitation and Refusal Mechanism
por: Cao, Lang
Publicado: (2023)

Beyond a Single Direction: Chain-of-Thought Disrupts Simple Steering of Refusal
por: Yang, Kia-Jüng, et al.
Publicado: (2026)

Beyond No: Quantifying AI Over-Refusal and Emotional Attachment Boundaries
por: Noever, David, et al.
Publicado: (2025)

Human Decision-Making with Persuasive and Narrative LLM Explanations
por: Marusich, Laura R., et al.
Publicado: (2026)

LatentRefusal: Latent-Signal Refusal for Unanswerable Text-to-SQL Queries
por: Ren, Xuancheng, et al.
Publicado: (2026)

Beyond the Attention Stability Boundary: Agentic Self-Synthesizing Reasoning Protocols
por: Shehata, Dahlia, et al.
Publicado: (2026)

Beyond Explicit Refusals: Soft-Failure Attacks on Retrieval-Augmented Generation
por: Zhang, Wentao, et al.
Publicado: (2026)

When Safety Blocks Sense: Measuring Semantic Confusion in LLM Refusals
por: Anonto, Riad Ahmed, et al.
Publicado: (2025)

VeriAct: Beyond Verifiability -- Agentic Synthesis of Correct and Complete Formal Specifications
por: Misu, Md Rakib Hossain, et al.
Publicado: (2026)

Blind Refusal: Language Models Refuse to Help Users Evade Unjust, Absurd, and Illegitimate Rules
por: Pattison, Cameron, et al.
Publicado: (2026)

Optimal Transport-Guided Adversarial Attacks on Graph Neural Network-Based Bot Detection
por: Mukherjee, Kunal, et al.
Publicado: (2026)

Optimizing Agentic Reasoning with Retrieval via Synthetic Semantic Information Gain Reward
por: Hu, Senkang, et al.
Publicado: (2026)

Beyond I'm Sorry, I Can't: Dissecting Large Language Model Refusal
por: Prakash, Nirmalendu, et al.
Publicado: (2025)

Beyond Semantic Similarity: Rethinking Retrieval for Agentic Search via Direct Corpus Interaction
por: Li, Zhuofeng, et al.
Publicado: (2026)

Beyond Compliance: How AI Could Help Creative Writers by Refusing Them
por: Qin, Hua Xuan, et al.
Publicado: (2026)

Improving Methodologies for Agentic Evaluations Across Domains: Leakage of Sensitive Information, Fraud and Cybersecurity Threats
por: Seah, Ee Wei, et al.
Publicado: (2026)

Refusal Before Decoding: Detecting and Exploiting Refusal Signals in Intermediate LLM Activations
por: Collu, Matteo Gioele, et al.
Publicado: (2026)

RefusalBench: Why Refusal Rate Misranks Frontier LLMs on Biological Research Prompts
por: Weidener, Lukas, et al.
Publicado: (2026)

Think Before Refusal : Triggering Safety Reflection in LLMs to Mitigate False Refusal Behavior
por: Si, Shengyun, et al.
Publicado: (2025)

Semantic Invariance in Agentic AI
por: de Zarzà, I., et al.
Publicado: (2026)

Beyond Output Critique: Self-Correction via Task Distillation
por: Rahmani, Hossein A., et al.
Publicado: (2026)

Refuse Whenever You Feel Unsafe: Improving Safety in LLMs via Decoupled Refusal Training
por: Yuan, Youliang, et al.
Publicado: (2024)

Can LLMs Refuse Questions They Do Not Know? Measuring Knowledge-Aware Refusal in Factual Tasks
por: Pan, Wenbo, et al.
Publicado: (2025)

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

Beyond the 'Diff': Addressing Agentic Entropy in Agentic Software Development
por: Casserini, Matteo, et al.
Publicado: (2026)

RefusalBench: Generative Evaluation of Selective Refusal in Grounded Language Models
por: Muhamed, Aashiq, et al.
Publicado: (2025)

GeoSR: Cognitive-Agentic Framework for Probing Geospatial Knowledge Boundaries via Iterative Self-Refinement
por: Tang, Jinfan, et al.
Publicado: (2025)