Goldfarb-Tarrant, Seraphina

3 publications

ICLR 2026 Learning Is Forgetting; LLM Training as Lossy Compression Henry Conklin, Tom Hosking, Tan Yi-Chern, Jonathan D. Cohen, Sarah-Jane Leslie, Thomas L. Griffiths, Max Bartolo, Seraphina Goldfarb-Tarrant

NeurIPSW 2024 "There Are No Solutions, Only Trade-Offs.'' Taking a Closer Look at Safety Data Annotations. Elle Michelle Yang, Matthias Gallé, Seraphina Goldfarb-Tarrant

NeurIPSW 2024 Mix Data or Merge Models? Optimizing for Performance and Safety in Multilingual Contexts Aakanksha, Arash Ahmadian, Seraphina Goldfarb-Tarrant, Beyza Ermis, Marzieh Fadaee, Sara Hooker