2 papers
cs.CR2026
Safety Anchor: Defending Harmful Fine-tuning via Geometric Bottlenecks
Guoxin Lu, Letian Sha, Qing Wang +4
The safety alignment of Large Language Models (LLMs) remains vulnerable to Harmful Fine-tuning (HFT). While existing defenses impose constraints on parameters, gradients, or intern…
cs.AI2025
On Path to Multimodal Historical Reasoning: HistBench and HistAgent
Jiahao Qiu, Fulian Xiao, Yimin Wang +96
Recent advances in large language models (LLMs) have led to remarkable progress across domains, yet their capabilities in the humanities, particularly history, remain underexplored…