Danqi Chen

7

Papers

600

Total Citations

1

Affiliations

Affiliations

Princeton University

Papers (7)

Catastrophic Jailbreak of Open-source LLMs via Exploiting Generation

SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal

Organize the Web: Constructing Domains Enhances Pre-Training Data Curation

Language Models as Science Tutors

QuRating: Selecting High-Quality Data for Training Language Models

Interpretability Illusions in the Generalization of Simplified Models

LESS: Selecting Influential Data for Targeted Instruction Tuning