arXiv Machine Learning July 1, 2026 By Zhichao Fan, Zexin Zhuang, Yanhang Li

Probe Choice Changes Canary-Memorization Verdicts: Three Post-Hoc Disagreement Case Studies in a Text-Dominant LoRA-Tuned Autoregressive Testbed

Read the original on arXiv Machine Learning →

arXiv:2606. 31168v1 Announce Type: cross Abstract: We audit a fixed prefix-window mean-NLL memorization probe (K=20) on a Qwen2.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

fine-tuning

arXiv AI

Aug 11

Do All LLMs Know When They're Being Harmful? A Reproducibility Study of Latent-Space Safety Probes Across Model Families

arXiv:2608. 08029v1 Announce Type: cross Abstract: Khatri et al.

By Alizishaan Khatri, Dun Li Chan

llms benchmarks safety

arXiv AI

Jul 8

Doomed from the Start: Early Abort of LLM Agent Episodes via a Recall-Controlled Probe Cascade

arXiv:2607. 06503v1 Announce Type: new Abstract: Large language model (LLM) agents solving multi-step tasks frequently commit to trajectories that are doomed to fail, yet continue to consume substantial inference compute before the failure becomes observable.

By Kai Ruan, Zihe Huang, Ziqi Zhou, Qianshan Wei, Xuan Wang, Hao Sun

llms agents

arXiv Machine Learning

Jun 2

CANARY: Zero-Label Detection of Fine-Tuning Contamination in Language Models

arXiv:2606. 01695v1 Announce Type: new Abstract: Adversaries can implant latent harmful behavior by poisoning as few as 1% of fine-tuning examples.

By Swapnil Parekh

llms fine-tuning safety

arXiv AI

Jun 30

Closing the Activation-Cone Blind Spot: Response-Time Probing and Unified Defense

arXiv:2606. 29441v1 Announce Type: cross Abstract: Inference-time safety methods for large language models have proliferated, yet no systematic comparison exists.

By Subhadip Mitra

llms benchmarks safety

arXiv Machine Learning

5d ago

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

Jun 9

Strained Coherence: A Pre-Failure Signal in Coding Agent Execution Trajectories

arXiv:2606. 07889v1 Announce Type: cross Abstract: LLM-based coding agents sometimes acknowledge a problem in their own reasoning and then proceed anyway.

By Marut Pandya, Kasey Zhang, Baiqing Lyu

llms agents safety

Related stories

Do All LLMs Know When They're Being Harmful? A Reproducibility Study of Latent-Space Safety Probes Across Model Families

Doomed from the Start: Early Abort of LLM Agent Episodes via a Recall-Controlled Probe Cascade

CANARY: Zero-Label Detection of Fine-Tuning Contamination in Language Models

Closing the Activation-Cone Blind Spot: Response-Time Probing and Unified Defense

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

Strained Coherence: A Pre-Failure Signal in Coding Agent Execution Trajectories