Refusal-ablated LLMs outperform aligned models on code-grounded localization and early executable patch generation, while aligned models retain advantages on shallow diagnostic tasks under neutral wording.
Refusal in language models is mediated by a single direction
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3representative citing papers
EVA applies direct model editing to surgically neutralize jailbreak vulnerabilities in LLMs and VLMs by targeting specific neurons while preserving general capabilities.
Salami Attack chains low-risk inputs to cumulatively trigger high-risk LLM behaviors, achieving over 90% success on GPT-4o and Gemini while resisting some defenses.
citing papers explorer
-
Beyond Refusal: A Same-Lineage Study of Aligned and Abliterated LLMs for Vulnerability Analysis
Refusal-ablated LLMs outperform aligned models on code-grounded localization and early executable patch generation, while aligned models retain advantages on shallow diagnostic tasks under neutral wording.
-
EVA: Editing for Versatile Alignment against Jailbreaks
EVA applies direct model editing to surgically neutralize jailbreak vulnerabilities in LLMs and VLMs by targeting specific neurons while preserving general capabilities.
-
The Salami Slicing Threat: Exploiting Cumulative Risks in LLM Systems
Salami Attack chains low-risk inputs to cumulatively trigger high-risk LLM behaviors, achieving over 90% success on GPT-4o and Gemini while resisting some defenses.