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, …
⏱ Độ trễ thật của tab này: trung bình 7.3 giờ sau khi CVE được công bố (n = 5337, sớm nhất 0.1 giờ). Số âm nghĩa là ta thấy trước ngày công bố.
23
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
🅲 hạng C
23
Denoising the US Census: Succinct Block Hierarchical Regression
arXiv:2603.10099v2 Announce Type: replace-cross Abstract: The 2020 United States Census adopted differential privacy to protect individual confidentiality, adding calibrated noise to summary demographic measurements that are then reconciled into population tables. We developed B…
🅲 hạng C
20
Rotated Robustness: A Training-Free Defense against Bit-Flip Attacks on Large Language Models
arXiv:2603.16382v3 Announce Type: replace Abstract: Bit-flip corruption of quantized weights poses a serious reliability threat to Large Language Models (LLMs), as even a small number of weight faults can trigger catastrophic model degradation. We show that such failures can be …
🅲 hạng C