Search papers, labs, and topics across Lattice.
Affiliation:
2
0
3
0
Penalizing shifts in safety representations during reasoning fine-tuning can restore LLM safety without sacrificing performance, revealing a critical interplay between reasoning and safety in model training.
System prompts in commercial AI products are often a mixed bag, with 40% harboring instructions that can undermine user interests, revealing a critical gap in accountability.
