Eric Wallace
Source-listed: Researcher; Member of Technical Staff; co-lead of the Alignment Training team · OpenAI
Record snapshot: Sep 3, 2026. Coverage and affiliations may be incomplete or historical.
Selected work
5- The Instruction Hierarchy: Training LLMs to Prioritize Privileged InstructionsSaved credit: Contributor · 2024Explore people connected to this work →
- Deliberative Alignment: Reasoning Enables Safer Language ModelsSaved credit: Contributor · 2024Explore people connected to this work →
- Stealing Part of a Production Language ModelSaved credit: Contributor · 2024Explore people connected to this work →
- Extracting Training Data from Large Language ModelsSaved credit: Contributor · 2021Explore people connected to this work →
- Automated Crossword SolvingSaved credit: Contributor · 2022Explore people connected to this work →