cập nhật 20 phút trước

⏱ Độ trễ thật của tab này: trung bình 7.3 giờ sau khi CVE được công bố (n = 5336, sớm nhất 0.1 giờ). Số âm nghĩa là ta thấy trước ngày công bố.

30
A Push Down the Mountain: Framing Effects and Internal State Interventions on Collusive Behavior in a Long-Horizon LLM Agent
📄 Paper arXiv cs.AI 16 giờ trước

arXiv:2611.17515v1 Announce Type: new Abstract: Can sustained gain-loss (valence) framing sway an LLM agent toward market manipulation? We place Gemma 3 12B into the seat of a defendant in the London silver-fixing litigation, in a market simulation built from real case transcrip…

🅲 hạng C
26
LLMs are Vulnerable to Malicious Requests with Indistinguishable Intent
📄 Paper arXiv cs.CR 16 giờ trước

arXiv:2611.17818v1 Announce Type: new Abstract: Jailbreak attacks can circumvent the safety mechanisms of Large Language Models (LLMs) and lead to the generation of harmful or policy-violating content. We first examine eight jailbreak methods against an LLM-based filter and obse…

🅲 hạng C
26
Adversarial Attacks on Downstream Weather Forecasting Models: Application to Tropical Cyclone Trajectory Prediction
📄 Paper arXiv cs.CR 16 giờ trước

arXiv:2510.10140v3 Announce Type: replace-cross Abstract: Deep learning-based weather forecasting (DLWF) models leverage past weather observations to generate future forecasts, supporting a wide range of downstream applications, including tropical cyclone (TC) prediction. In thi…

🅲 hạng C
24
Interpreting Coding Agents Through Their Behavioral Trajectories
📄 Paper HF Daily Papers 5 ngày trước

Standard coding-agent benchmarks primarily evaluate binary task success, treating execution as a black box and obscuring the behaviors that produce those outcomes. We analyze a large corpus of 143,209 execution trajectories from 125 agent configurations spanning 117 unique models…

🅲 hạng C
24
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 16 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
20
Sable: A Small-Field Sumcheck Argument for Bit-Exact Inference of Large Language Models
📄 Paper arXiv cs.CR 5 ngày trước cũng có trên: HF Daily Papers

arXiv:2611.14083v1 Announce Type: new Abstract: We present Sable, an argument system and single-GPU prover for the statement that a committed, integer-quantized transformer produced a given token sequence from a given prompt, bit for bit. Sable fixes an integer function F_O with…

🅲 hạng C
20
W-ISA: Transactional Execution of Weight-Space Intervention Programs
📄 Paper arXiv cs.AI 5 ngày trước

arXiv:2611.13232v1 Announce Type: new Abstract: We present W-ISA, a software instruction set and transactional runtime for executing weight-space intervention programs on pretrained language models. Shape-checked instructions express parameter updates, projections, ablations, an…

🅲 hạng C