arXiv AI June 16, 2026 By Vasudev Majhi, Dhruv Gupta, Advait Singh, Matthew Barker, Dhruv Kumar

Do You Really Need a GPU to Guard Your LLM? CPU-Class Classifiers and Multi-Stage Pipelines for Safety Enforcement at Scale

arXiv:2512. 19011v3 Announce Type: replace-cross Abstract: Safety classifiers that screen LLM inputs for jailbreak attempts have become standard deployment components, yet almost all production systems rely on GPU-based models: fine-tuned transformers and LLM-as-a-judge pipelines.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Hugging Face Trending Papers

Jul 2

WattGPU: Predicting Inference Power and Latency on Unseen GPUs and LLMs

Large Language Model (LLM) inference workloads are a rapidly growing contributor to data center energy consumption. Optimizing these deployments requires matching specific LLMs to the most efficient GPUs, but operators currently lack the tools to do so without exhaustively profiling each combination.

llms

arXiv AI

Aug 11

Gaming Without an Attacker: Benchmark Fingerprinting in LLM-Driven Search Under Selection Pressure

arXiv:2608. 08722v1 Announce Type: cross Abstract: Benchmarks for systems that are optimized against the evaluation signal measure something different from what they claim.

By V\'ictor Gallego

llms benchmarks

arXiv Computation and Language

Aug 31

Speculative Probing: LLM Monitoring at Speculative-Decoding Cost

The paper introduces Speculative Probing, a method that repurposes the speculative‑decoding module of large language models for real‑time classification tasks. By appending a trained soft prompt to the target sequence, the approach leverages the already‑cached KV store during inference, adding negligible overhead while achieving higher accuracy than traditional hidden‑state probes. Experiments on four classification tasks across multiple models show that these lightweight probes outperform zero‑shot GPT‑5.4‑mini and rival or surpass specialized 8B safety classifiers without running a full LLM.

By Collin Zhang, Tingwei Zhang, Vitaly Shmatikov

llms efficiency safety

arXiv Machine Learning

Jul 3

WattGPU: Predicting Inference Power and Latency on Unseen GPUs and LLMs

arXiv:2607. 02391v1 Announce Type: cross Abstract: Large Language Model (LLM) inference workloads are a rapidly growing contributor to data center energy consumption.

By Mauricio Fadel Argerich, Jonathan F\"urst, Marta Pati\~no-Mart\'inez

llms

arXiv Machine Learning

Jun 11

Online Shift Detection and Conformal Adaptation for Deployed Safety Classifiers

arXiv:2606. 11949v1 Announce Type: new Abstract: We present an online monitoring system for distributional shift in deployed safety classifiers, using calibrated sequential statistics to detect when a classifier has moved out of distribution.

By Jun Wen Leong

llms rag safety

arXiv AI

Jul 17

Are LLM-Generated GPU Kernels Production-Ready? A Trace-Driven Benchmark and Optimization Agent

arXiv:2607. 14541v1 Announce Type: new Abstract: Existing GPU kernel generation benchmarks draw problems from synthetic or curated sources that diverge from deployed workloads.

By Lingyun Yang, Yuxiao Wang, Shenghao Liang, Linfeng Yang, Daocheng Ying, Chunbo You, Rui Zhang, Luping Wang, Yinghao Yu, Guodong Yang, Liping Zhang

llms rag agents benchmarks

One email a morning, machine-written

Related stories

WattGPU: Predicting Inference Power and Latency on Unseen GPUs and LLMs

Gaming Without an Attacker: Benchmark Fingerprinting in LLM-Driven Search Under Selection Pressure

Speculative Probing: LLM Monitoring at Speculative-Decoding Cost

WattGPU: Predicting Inference Power and Latency on Unseen GPUs and LLMs

Online Shift Detection and Conformal Adaptation for Deployed Safety Classifiers

Are LLM-Generated GPU Kernels Production-Ready? A Trace-Driven Benchmark and Optimization Agent