Steven Basart

Identifiers

• name variant Steven Basart 0.60 · backfill

Papers (7)

1. The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning cs.LG · 2024 · author #46
2. HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal cs.LG · 2024 · author #9
3. Representation Engineering: A Top-Down Approach to AI Transparency cs.LG · 2023 · author #16
4. Measuring Coding Challenge Competence With APPS cs.SE · 2021 · author #2
5. Measuring Mathematical Problem Solving With the MATH Dataset cs.LG · 2021 · author #5
6. Measuring Massive Multitask Language Understanding cs.CY · 2020 · author #3
7. Aligning AI With Shared Human Values cs.CY · 2020 · author #3

Mentions

• 2008.02275 #3 · arxiv_oai · confidence 0.70 Steven Basart
• 2403.03218 #46 · arxiv_oai · confidence 0.70 Steven Basart

Frequent Coauthors

• Dan Hendrycks 7 shared papers
• Dawn Song 5 shared papers
• Mantas Mazeika 5 shared papers
• Andy Zou 4 shared papers
• Collin Burns 4 shared papers
• Jacob Steinhardt 4 shared papers
• Long Phan 3 shared papers
• Nathaniel Li 3 shared papers
• Zifan Wang 3 shared papers
• Akul Arora 2 shared papers
• Alexander Pan 2 shared papers
• Ann-Kathrin Dombrowski 2 shared papers
• Saurav Kadavath 2 shared papers
• Shashwat Goel 2 shared papers
• Xuwang Yin 2 shared papers
• Adam A. Hunt 1 shared papers
• Adam Khoja 1 shared papers
• Alexandr Wang 1 shared papers
• Alex Levinson 1 shared papers
• Alex Mallen 1 shared papers