← Search

Karim Elmaaroufi

2 accepted papers

2024

Synthetic Programming Elicitation for Text-to-Code in Very Low-Resource Programming and Formal Languages

NeurIPS 2024poster

Recent advances in large language models (LLMs) for code applications have demonstrated remarkable zero-shot fluency and instruction following on challenging code related tasks ranging from test case generation to self-repair. Unsurprisingly, however, models struggle to compose syntactically valid p…

2024

Tensor Trust: Interpretable Prompt Injection Attacks from an Online Game

ICLR 2024spotlight

While Large Language Models (LLMs) are increasingly being used in real-world applications, they remain vulnerable to *prompt injection attacks*: malicious third party prompts that subvert the intent of the system designer. To help researchers study this problem, we present a dataset of over 563,000…

Cited by 86SourcePDFScholar