Nathaniel Li

3 papers · 2023–2024 · 1 venue · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌉 Interdisciplinary Bridge · Bronze 🐣 Hot Topic Early Bird 👥 Mega-Team · Squad ❓ The Questioner

Venues

ICML (3)

Top co-authors

Steven Basart (3) Andy Zou (3) Dan Hendrycks (3) Mantas Mazeika (2) Zifan Wang (2) Alexander Pan (2) Long Phan (1) Adam Alfred Hunt (1) David Campbell (1) Uday Tupakula (1)

Research topics

Natural Language Processing (3) Artificial Intelligence (2) Machine Learning (2) Core AI (2) Resources & Methods (2) Application Areas (1) Applications (1) Core Methods (1)

Keywords

large language model (2) evaluation framework (1) reward optimization (1) ethical behavior (1) machine ethics (1) automated red teaming (1) unlearning (1) malicious use (1) robust refusal (1) hazardous knowledge (1) biosecurity (1) proxy measurement (1) adversarial training (1) wmdp benchmark (1)

Papers

HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal ICML 2024 The WMDP Benchmark: Measuring and Reducing Malicious Use with Unlearning ICML 2024 Do the Rewards Justify the Means? Measuring Trade-Offs Between Rewards and Ethical Behavior in the Machiavelli Benchmark ICML 2023