arXiv Machine Learning June 19, 2026 By Milo\v{s} Nikoli\'c, Ali Hadi Zadeh, Enrique Torres Sanchez, Andreas Moshovos

Displacement Is Not Direction: Evaluating Fidelity Metrics for Quantized LLM Deployment

Read the original on arXiv Machine Learning →

arXiv:2606. 19558v1 Announce Type: new Abstract: Fidelity metrics, such as per-token KL divergence (KLD) against a high-precision reference, are often used in practice as low-cost proxies for benchmark quality.

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 Machine Learning.

arXiv Machine Learning

Jul 31

Flat Score, Amplified Failures: How the Error Budget Masks Damage in Quantized LLM Agents

arXiv:2607. 27275v1 Announce Type: new Abstract: Post-training quantization to 4-bit weights is widely reported to be nearly lossless.

By Jiwon Jang, Kisu Yang, Heuiseok Lim, Hyunwoo Park

llms agents efficiency benchmarks safety

arXiv AI

2d ago

How Divergence Becomes Decision Flips in Compressed Language Models

arXiv:2610.00694v1 Announce Type: cross Abstract: Compression reports summarize how far a compressed language model moved from the dense one, usually by a KL divergence; a deployment that relies on t...

By Beatriz Almeida Felicio

llms

arXiv AI

Aug 18

Ventor-QTest: Threat-Model-Driven Verification of Vendor-Hosted LLM APIs

arXiv:2608. 16391v1 Announce Type: cross Abstract: As large language models become increasingly widespread, third-party providers that deploy open-weight models have become an important part of the ecosystem.

By Xiangfan Wu, Zonghao Ying, Huiyu Wu, Xing Zheng, Huangsheng Cheng, Xiaorong Shi, Jing Guo

llms agents safety

arXiv Machine Learning

Aug 14

Excess Separability: Nuisance-Controlled Residual-Stream Probing for Benchmark Contamination Detection

arXiv:2608. 12652v1 Announce Type: cross Abstract: Benchmark contamination is diagnosed today with n-gram overlap, with likelihood-based membership inference, or with canary strings, and each needs something usually unavailable: the training corpus, a well-chosen test statistic, or foresight at dataset release.

By Florian Braun

llms benchmarks

arXiv AI

Sep 10

Quantization Amplifies Determinism, Not Bias: Scale-Dependent Behavioral Effects of Serving-Time Weight Compression

arXiv:2609.07901v1 Announce Type: new Abstract: Weight quantization largely determines the economics of serving open-weight LLMs. Its costs are usually assessed with capability benchmarks, on which 4...

By Dachi Kurtskhalia

llms efficiency benchmarks safety

arXiv Machine Learning

Aug 11

Which Decisions Low-Bit Quantization Breaks, and How to Predict Them

arXiv:2608. 06564v2 Announce Type: replace Abstract: Quantization is how large language models are actually deployed, and below four bits it hurts.

By Zekun Wu, Swati Dhiman, Adriano Koshiyama

llms agents efficiency benchmarks safety

One email a morning, machine-written

Related stories

Flat Score, Amplified Failures: How the Error Budget Masks Damage in Quantized LLM Agents

How Divergence Becomes Decision Flips in Compressed Language Models

Ventor-QTest: Threat-Model-Driven Verification of Vendor-Hosted LLM APIs

Excess Separability: Nuisance-Controlled Residual-Stream Probing for Benchmark Contamination Detection

Quantization Amplifies Determinism, Not Bias: Scale-Dependent Behavioral Effects of Serving-Time Weight Compression

Which Decisions Low-Bit Quantization Breaks, and How to Predict Them