arXiv AI September 30, 2026 By Taeung Yoon, Yupeng Zhang, Xiaojing Liao

Bits Under ZK-LLM: Evaluating Zero-Knowledge-Friendly Quantization for Verifiable Private LLM Inference

The paper introduces the first systematic study of zero‑knowledge (ZK)‑friendly quantization for large language models (LLMs). It defines what makes a quantization scheme suitable for ZK proof generation and evaluates nine models, including Qwen2.5‑14B and Qwen3‑30B‑A3B, across various weight, activation, and nonlinear lookup precisions. Findings reveal that activation precision is more critical than weight precision, nonlinear lookup approximations can dominate utility loss, and that reducing bit‑width or lookup size does not always lead to proportional proving cost savings, highlighting the need for operator‑aware precision selection.

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.

arXiv AI

Jul 21

NanoZK: Privacy-Preserving Verifiable Inference for Large Language Models via Layerwise Zero-Knowledge Proofs

arXiv:2603. 18046v2 Announce Type: replace-cross Abstract: We present NanoZK, a zero-knowledge proof system for verifiable LLM inference: clients and third-party auditors check that a provider executed the advertised model on a committed input without learning weights or activations.

By Zhaohui Wang

llms safety

Hugging Face Trending Papers

Jun 2

Testing LLM Arithmetic Reasoning Generalization with Automatic Numeric-Remapping Attacks

Large language models achieve strong performance on arithmetic reasoning benchmarks, and one common response to arithmetic brittleness is to delegate computation to code. Yet models are still often used in settings where they must reason directly from natural language, and trustworthy models should solve small-number arithmetic word problems without external tools.

llms benchmarks

arXiv AI

Jun 3

Testing LLM Arithmetic Reasoning Generalization with Automatic Numeric-Remapping Attacks

arXiv:2606. 03606v1 Announce Type: cross Abstract: Large language models achieve strong performance on arithmetic reasoning benchmarks, and one common response to arithmetic brittleness is to delegate computation to code.

By Malia Barker, Bishal Lakha, Edoardo Serra, Francesco Gullo

llms benchmarks

arXiv Machine Learning

Jun 8

AAAC: Activation-Aware Adaptive Codebooks for 4-bit LLM Weight Quantization

arXiv:2605. 08692v2 Announce Type: replace Abstract: Post-training weight-only quantization to 4 bits is widely used to reduce the memory and compute costs of large language model inference.

By Beshr IslamBouli, David Jin

llms efficiency

arXiv AI

Aug 3

When Bits Break Recourse: Counterfactual-Faithful Quantization

arXiv:2605. 17160v2 Announce Type: replace-cross Abstract: Model quantization is widely used to reduce memory, latency, and deployment cost, and is typically judged by whether predictive accuracy is preserved.

By Chaymae Yahyati, Ismail Lamaakal, Khalid El Makkaoui, Ibrahim Ouahbi

efficiency

arXiv Machine Learning

Jul 7

Lipschitz-Based Robustness Certification Under Floating-Point Execution

arXiv:2603. 13334v4 Announce Type: replace Abstract: Lipschitz-based robustness certification bounds a network's sensitivity through concrete numerical computation rather than symbolic reasoning, and so scales efficiently.

By Toby Murray

One email a morning, machine-written

Related stories

NanoZK: Privacy-Preserving Verifiable Inference for Large Language Models via Layerwise Zero-Knowledge Proofs

Testing LLM Arithmetic Reasoning Generalization with Automatic Numeric-Remapping Attacks

Testing LLM Arithmetic Reasoning Generalization with Automatic Numeric-Remapping Attacks

AAAC: Activation-Aware Adaptive Codebooks for 4-bit LLM Weight Quantization

When Bits Break Recourse: Counterfactual-Faithful Quantization

Lipschitz-Based Robustness Certification Under Floating-Point Execution