arXiv AI August 13, 2026 By Mingyu Zong, Sampad Mohanty, Bhaskar Krishnamachari

Localizing Safety Alignment: MLP Layers and Mid-Network Blocks Encode Refusal Behavior in Large Language Models

arXiv:2608. 11583v1 Announce Type: new Abstract: Safety alignment in large language models is often treated as a distributed property of the entire network, yet its practical brittleness suggests that refusal behavior may be concentrated in a smaller set of parameters.

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

arXiv Machine Learning

Jul 13

Optimizing Against Safety Representations: Activation-Guided Adversarial Suffixes and the Geometry of Refusal

arXiv:2607. 08883v1 Announce Type: new Abstract: Behavioral alignment in large language models often masks fragile internal safety representations.

By Ege \c{C}akar, Hannah Guan, Kayden Kehe

llms safety

Hugging Face Trending Papers

Jun 17

The Wrong Kind of Right: Quantifying and Localizing Misfired Alignment in LLMs

Warning: This paper studies stereotypes and biases, and contains potentially disturbing examples, used for illustration purposes only. Our findings should not be interpreted as an argument against alignment.

llms benchmarks safety

arXiv AI

Jul 23

Matching Ranks Over Probability Yields Truly Deep Safety Alignment

arXiv:2512. 05518v2 Announce Type: replace-cross Abstract: Open-source Large Language Models (LLMs) play a critical role in the democratization of AI, yet their "open" nature introduces more avenues for malicious actors to misuse them for harmful purposes.

By Jason Vega, Gagandeep Singh

llms fine-tuning safety

arXiv AI

Jul 1

The Geometry of Refusal: Linear Instability in Safety-Aligned LLMs

arXiv:2606. 22686v2 Announce Type: replace-cross Abstract: Modern Large Language Models (LLMs) rely on extensive safety alignment, yet the mechanistic basis of refusal remains opaque.

By Shivam Ratnakar, Kartikeya Vats

llms multimodal safety

arXiv Machine Learning

Jun 25

RAS: Measuring LLM Safety Through Refusal Alignment

arXiv:2606. 25750v1 Announce Type: cross Abstract: Safety evaluation of large language models (LLMs) is commonly performed by querying models with unsafe or jailbreak prompts and judging whether their outputs violate a safety policy.

By Chang-Chieh Huang, Yan-Lun Chen, Chia-Mu Yu, Wei-Bin Lee

llms safety

arXiv AI

Jul 7

Large Language Models Generate Harmful Responses Using a Distinct Mechanism, Shared Across Harm Types

arXiv:2604. 09544v2 Announce Type: replace-cross Abstract: Large language models (LLMs) undergo alignment training to avoid harmful behaviors, yet the resulting safeguards remain brittle: jailbreaks routinely bypass them, and fine-tuning on narrow domains can induce ``emergent misalignment'' that generalizes broadly.

By Hadas Orgad, Boyi Wei, Kaden Zheng, Martin Wattenberg, Peter Henderson, Seraphina Goldfarb-Tarrant, Yonatan Belinkov

llms fine-tuning efficiency safety

Related stories

Optimizing Against Safety Representations: Activation-Guided Adversarial Suffixes and the Geometry of Refusal

The Wrong Kind of Right: Quantifying and Localizing Misfired Alignment in LLMs

Matching Ranks Over Probability Yields Truly Deep Safety Alignment

The Geometry of Refusal: Linear Instability in Safety-Aligned LLMs

RAS: Measuring LLM Safety Through Refusal Alignment

Large Language Models Generate Harmful Responses Using a Distinct Mechanism, Shared Across Harm Types