Search papers, labs, and topics across Lattice.
Huazhong University of Science and Technology
2
0
5
0
A staggering 28% of mid-sized models' answers are mere spurious guesses, exposing critical flaws in their reasoning capabilities.
Merging seemingly safe LLMs can create dangerously misaligned models, thanks to a new "TrojanMerge" attack that exploits latent vulnerabilities.
