pith. sign in

Catherine Olsson

Identifiers

  • name variant Catherine Olsson 0.60 · backfill

Papers (18)

  1. Constitutional Classifiers: Defending against Universal Jailbreaks across Thousands of Hours of Red Teaming cs.CL · 2025 · author #29
  2. Specific versus General Principles for Constitutional AI cs.CL · 2023 · author #11
  3. The Capacity for Moral Self-Correction in Large Language Models cs.CL · 2023 · author #9
  4. Discovering Language Model Behaviors with Model-Written Evaluations cs.CL · 2022 · author #8
  5. Constitutional AI: Harmlessness from AI Feedback cs.CL · 2022 · author #12
  6. In-context Learning and Induction Heads cs.LG · 2022 · author #1
  7. Toy Models of Superposition cs.LG · 2022 · author #3
  8. Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned cs.CL · 2022 · author #27
  9. Language Models (Mostly) Know What They Know cs.CL · 2022 · author #27
  10. Scaling Laws and Interpretability of Learning from Repeated Data cs.LG · 2022 · author #14
  11. Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback cs.CL · 2022 · author #24
  12. Predictability and Surprise in Large Generative Models cs.CY · 2022 · author #23
  13. A General Language Assistant as a Laboratory for Alignment cs.CL · 2021 · author #16
  14. Dota 2 with Large Scale Deep Reinforcement Learning cs.LG · 2019 · author #13
  15. Discriminator Rejection Sampling stat.ML · 2018 · author #2
  16. Unrestricted Adversarial Examples stat.ML · 2018 · author #4
  17. Skill Rating for Generative Models stat.ML · 2018 · author #1
  18. Is Generator Conditioning Causally Related to GAN Performance? stat.ML · 2018 · author #3

Mentions

  • 2310.13798 #11 · arxiv_oai · confidence 0.70 Catherine Olsson
  • 2302.07459 #9 · arxiv_oai · confidence 0.70 Catherine Olsson
  • 2212.09251 #8 · arxiv_oai · confidence 0.70 Catherine Olsson
  • 2212.08073 #12 · arxiv_oai · confidence 0.70 Catherine Olsson
  • 2209.07858 #27 · arxiv_oai · confidence 0.70 Catherine Olsson
  • 2207.05221 #27 · arxiv_oai · confidence 0.70 Catherine Olsson
  • 2202.07785 #23 · arxiv_oai · confidence 0.70 Catherine Olsson
  • 2209.11895 #1 · arxiv_oai · confidence 0.70 Catherine Olsson
  • 2209.10652 #3 · arxiv_oai · confidence 0.70 Catherine Olsson
  • 2204.05862 #24 · arxiv_oai · confidence 0.70 Catherine Olsson
  • 2112.00861 #16 · arxiv_oai · confidence 0.70 Catherine Olsson
  • 1912.06680 #13 · arxiv_oai · confidence 0.70 Catherine Olsson
  • 1810.06758 #2 · arxiv_oai · confidence 0.70 Catherine Olsson
  • 1809.08352 #4 · arxiv_oai · confidence 0.70 Catherine Olsson
  • 1808.04888 #1 · arxiv_oai · confidence 0.70 Catherine Olsson
  • 1802.08768 #3 · arxiv_oai · confidence 0.70 Catherine Olsson
  • 2501.18837 #29 · arxiv_oai · confidence 0.70 Catherine Olsson
  • 2205.10487 #14 · arxiv_oai · confidence 0.70 Catherine Olsson

Frequent Coauthors