arXiv Machine Learning July 7, 2026 By Ananth Eswar, Pratinav Seth, Utsav Avaiya, Vinay Kumar Sankarapu

Faithfulness to Refusal: A Causal Audit of Neuron Selectors

Read the original on arXiv Machine Learning →

arXiv:2607. 05355v1 Announce Type: cross Abstract: Attribution scores increasingly identify which neuron rows of a language model matter for applications such as pruning, interpretability, and editing for safety, yet whether they identify causally important rows is rarely tested directly.

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

Sep 22

Knowing, and Saying It Only When Asked: LLM Endognostics and the Schizognosis of Minerva-7B

arXiv:2609.22219v1 Announce Type: cross Abstract: Evaluating an aligned language model by reading its answers assumes the answers carry the distinction the evaluator cares about. We introduce LLM end...

By Fabrizio Davide, Francesco Collova

llms benchmarks

arXiv AI

Aug 5

When Refusal Looks Safe: The Refusal-Cue Shortcut in Safety Guard Models

arXiv:2608. 03201v1 Announce Type: new Abstract: Safety guards are widely used to filter harmful content and are typically trained via supervised fine-tuning on labeled prompt-response pairs.

By Yu Feng, Chunting Zang, Chen Shen, Rui Miao, Ge Teng, Weidong Cai, Jieping Ye

fine-tuning benchmarks safety

arXiv AI

Sep 15

Calibrating Interpretability Instruments Before Trusting Their Verdicts

arXiv:2609.14754v1 Announce Type: cross Abstract: Causal claims about large language model (LLM) internals rest on measurements. Those might include a projection, a cosine, an ablation delta, or an i...

By Orion Reblitz-Richardson

llms benchmarks safety

arXiv AI

Aug 17

Tripwire: Triggering Aligned Refusal via Statistically Certified Safety Neurons

arXiv:2608. 14392v1 Announce Type: new Abstract: Neuron- and path-level interventions offer the finest-grained route to defending large language models (LLMs) against jailbreak attacks, yet existing methods fall short of this promise, i.

By Wei Zhao, Zhe Li, Peixin Zhang, Jun Sun

llms safety

arXiv AI

Aug 25

Proxy reliance in large language model decisions is uncalibrated to predictive evidence

arXiv:2608.22887v1 Announce Type: new Abstract: Large language models (LLMs) are entering decisions in triage and lending, where task-relevant inference must be distinguished from impermissible proxy...

By Zengqing Wu, Chuan Xiao

llms

arXiv AI

Sep 2

From Detection to Refusal: Safer LLMs via Circuit-Guided Weight Scaling

arXiv:2609.00051v1 Announce Type: cross Abstract: Despite extensive alignment efforts, Large Language Models (LLMs) remain vulnerable to generating unsafe content under adversarial prompting, yet the...

By Kuan-Lin Chu, Chung-En Sun, Tsui-Wei Weng

llms benchmarks safety

One email a morning, machine-written

Related stories

Knowing, and Saying It Only When Asked: LLM Endognostics and the Schizognosis of Minerva-7B

When Refusal Looks Safe: The Refusal-Cue Shortcut in Safety Guard Models

Calibrating Interpretability Instruments Before Trusting Their Verdicts

Tripwire: Triggering Aligned Refusal via Statistically Certified Safety Neurons

Proxy reliance in large language model decisions is uncalibrated to predictive evidence

From Detection to Refusal: Safer LLMs via Circuit-Guided Weight Scaling