Search papers, labs, and topics across Lattice.
Affiliation:
4
6
7
12
MidTool reveals that dedicated mid-training can significantly enhance LLMs' ability to utilize tools effectively, outperforming traditional post-training approaches.
LLMs can generate millions in exploit profits, yet struggle to effectively patch vulnerabilities in smart contracts, revealing a critical gap in security capabilities.
The best LLM to answer a question isn't always the best LLM to *teach* the answer, and matching the "difficulty" of the explanation to the student's current abilities yields better learning.
Despite claims of safety alignment, state-of-the-art LLMs still spill the beans on hazardous scientific knowledge at an alarming rate, failing nearly 80% of the time on a new regulation-grounded benchmark.
