cập nhật 17 phút trước

⏱ Độ trễ thật của tab này: trung bình 7.1 giờ sau khi CVE được công bố (n = 5351, sớm nhất 0.1 giờ). Số âm nghĩa là ta thấy trước ngày công bố.

25
Is Abliteration Getting Harder? Not Uniformly: Refusal Removal by Direction-Based Ablation and ARA in Heretic on the Qwen3.8, Gemma 4, Olmo 3.1 and Mistral Small 3.2 LLMs Versus Their Predecessors
📄 Paper arXiv cs.AI 5 giờ trước

arXiv:2611.17846v1 Announce Type: new Abstract: Abliteration, a fine-tuning-free weight edit, removes refusal from open-weight large language models (LLMs). The developer of Arbitrary-Rank Ablation (ARA), an optimisation-based variant, reports that direction-based abliteration, …

🅲 hạng C
21
Stress-Testing Sandbagging Detection Under Adaptive Attack
📄 Paper arXiv cs.CR 3 ngày trước

arXiv:2611.14950v1 Announce Type: new Abstract: Developers, auditors and researchers read evaluation scores as evidence of what a model can do. A model that sandbags, scoring low on purpose while keeping the capability, turns a low score into false reassurance. Sandbagging detec…

🅲 hạng C
20
What Is the Value of AI-Involved Art? Evidence From a Juried In-Person Exhibition
📄 Paper arXiv cs.AI 6 ngày trước

arXiv:2611.10150v1 Announce Type: new Abstract: What is the value of AI-involved art, and to whom does it belong? We begin to answer these questions using data from an in-person, juried AI art exhibition. Our study involved artists, lawyers, and computer scientists (N=209) as ei…

🅲 hạng C