Imagen de Portada

A Paired Testing Protocol for Batch-Conditioned Refusal Robustness in LLM Serving

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autor principal:	Kadadekar, Sahil
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Understanding Efficiency: Quantization, Batching, and Serving Strategies in LLM Energy Use
por: Delavande, Julien, et al.
Publicado: (2026)

RW-TTT: Batched Serving for Request-Owned Test-Time Training State
por: Yang, Jian, et al.
Publicado: (2026)

On Using Large-Batches in Federated Learning
por: Tyagi, Sahil
Publicado: (2025)

Tula: Optimizing Time, Cost, and Generalization in Distributed Large-Batch Training
por: Tyagi, Sahil, et al.
Publicado: (2026)

Robust Batched Bandits
por: Guo, Yunwen, et al.
Publicado: (2025)

Programming Refusal with Conditional Activation Steering
por: Lee, Bruce W., et al.
Publicado: (2024)

Targeted Tests for LLM Reasoning: An Audit-Constrained Protocol
por: Li, Hongmin
Publicado: (2026)

Efficient Refusal Ablation in LLM through Optimal Transport
por: Nanfack, Geraldin, et al.
Publicado: (2026)

BlendServe: Optimizing Offline Inference for Auto-regressive Large Models with Resource-aware Batching
por: Zhao, Yilong, et al.
Publicado: (2024)

Tracing the Dynamics of Refusal: Exploiting Latent Refusal Trajectories for Robust Jailbreak Detection
por: Hu, Xulin, et al.
Publicado: (2026)

Automated Network Protocol Testing with LLM Agents
por: Wei, Yunze, et al.
Publicado: (2025)

Symphony: Optimized DNN Model Serving using Deferred Batch Scheduling
por: Chen, Lequn, et al.
Publicado: (2023)

Refusal Tokens: A Simple Way to Calibrate Refusals in Large Language Models
por: Jain, Neel, et al.
Publicado: (2024)

DuetServe: Harmonizing Prefill and Decode for LLM Serving via Adaptive GPU Multiplexing
por: Gao, Lei, et al.
Publicado: (2025)

Apt-Serve: Adaptive Request Scheduling on Hybrid Cache for Scalable LLM Inference Serving
por: Gao, Shihong, et al.
Publicado: (2025)

High-Dimensional Robust Mean Estimation with Untrusted Batches
por: Aliakbarpour, Maryam, et al.
Publicado: (2026)

The CAP Principle for LLM Serving: A Survey of Long-Context Large Language Model Serving
por: Zeng, Pai, et al.
Publicado: (2024)

Paired Wasserstein Autoencoders for Conditional Sampling
por: Piening, Moritz, et al.
Publicado: (2024)

Model Equality Testing: Which Model Is This API Serving?
por: Gao, Irena, et al.
Publicado: (2024)

On the Role of Batch Size in Stochastic Conditional Gradient Methods
por: Islamov, Rustem, et al.
Publicado: (2026)

The Conditional Regret-Capacity Theorem for Batch Universal Prediction
por: Bondaschi, Marco, et al.
Publicado: (2025)

Robust Reward Alignment via Hypothesis Space Batch Cutting
por: Xie, Zhixian, et al.
Publicado: (2025)

Higher-Order Asymptotics of Test-Time Adaptation for Batch Normalization Statistics
por: Kimura, Masanari
Publicado: (2025)

HumorReject: Decoupling LLM Safety from Refusal Prefix via A Little Humor
por: Wu, Zihui, et al.
Publicado: (2025)

Doubly Robust Conditional Independence Testing with Generative Neural Networks
por: Zhang, Yi, et al.
Publicado: (2024)

Steering Language Model Refusal with Sparse Autoencoders
por: O'Brien, Kyle, et al.
Publicado: (2024)

Refusal in LLMs is an Affine Function
por: Marshall, Thomas, et al.
Publicado: (2024)

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

MEPIC: Memory Efficient Position Independent Caching for LLM Serving
por: Wang, Qian, et al.
Publicado: (2025)

Atom: Low-bit Quantization for Efficient and Accurate LLM Serving
por: Zhao, Yilong, et al.
Publicado: (2023)

NeuroCUT: A Neural Approach for Robust Graph Partitioning
por: Shah, Rishi, et al.
Publicado: (2023)

Efficient Conditioning Why Pseudo Observation Batch Bayesian Optimization Works When It Does not
por: Nagaswetha, Kumbha, et al.
Publicado: (2026)

An Interpretable Latency Model for Speculative Decoding in LLM Serving
por: Kong, Linghao, et al.
Publicado: (2026)

Rubric-Conditioned LLM Grading: Alignment, Uncertainty, and Robustness
por: Deng, Haotian, et al.
Publicado: (2025)

BatchLLM: Optimizing Large Batched LLM Inference with Global Prefix Sharing and Throughput-oriented Token Batching
por: Zheng, Zhen, et al.
Publicado: (2024)

Risk-Aware Batch Testing for Performance Regression Detection
por: Sayedsalehi, Ali, et al.
Publicado: (2026)

When Refusals Fail: Unstable Safety Mechanisms in Long-Context LLM Agents
por: Hadeliya, Tsimur, et al.
Publicado: (2025)

Adaptive Batch Normalization Networks for Adversarial Robustness
por: Lo, Shao-Yuan, et al.
Publicado: (2024)

OVERT: A Benchmark for Over-Refusal Evaluation on Text-to-Image Models
por: Cheng, Ziheng, et al.
Publicado: (2025)

WarmServe: Enabling One-for-Many GPU Prewarming for Multi-LLM Serving
por: Lou, Chiheng, et al.
Publicado: (2025)