Daniel Khashabi

6

Papers

30

Total Citations

1

Affiliations

Affiliations

Johns Hopkins University

Papers (6)

Controllable Safety Alignment: Inference-Time Adaptation to Diverse Safety Requirements

Error Norm Truncation: Robust Training in the Presence of Data Noise for Text Generation Models

SIMPLEMIX: Frustratingly Simple Mixing of Off- and On-policy Data in Language Model Preference Learning

SELF-[IN]CORRECT: LLMs Struggle with Discriminating Self-Generated Responses

WorldAPIs: The World Is Worth How Many APIs? A Thought Experiment

Position: Do pretrained Transformers Learn In-Context by Gradient Descent?