Oliver Rausch
Source-listed: Anthropic
Record snapshot: Sep 3, 2026. Coverage and affiliations may be incomplete or historical.
Selected work
5- Discovering Language Model Behaviors with Model-Written EvaluationsSaved credit: Contributor · 2022Explore people connected to this work →
- Towards Understanding Sycophancy in Language ModelsSaved credit: Contributor · 2023Explore people connected to this work →
- Measuring Faithfulness in Chain-of-Thought ReasoningSaved credit: Contributor · 2023Explore people connected to this work →
- A Data-Centric Optimization Framework for Machine LearningSaved credit: First author · 2022Explore people connected to this work →
- Evaluating feature steering: A case study in mitigating social biasesSaved credit: Contributor · 2024Explore people connected to this work →