Tag
This paper empirically measures how ten linguistic features in fine-tuning data shift Llama-3.2-1B's reasoning on animal welfare, finding that assertive and moral language strengthens pro-animal-welfare stances while hedged and descriptive language dilutes them.
This paper demonstrates that a small coordinated Wikipedia editing campaign can measurably shape how language models handle topics, using animal welfare as a case study.
Marwell Zoo and the University of Surrey are launching a three-year AI camera project to monitor nocturnal activity of giraffes and red river hogs, aiming to detect health issues early and improve welfare.