Negin Raoof

I’m a third year PhD student at UC Berkeley, advised by Alex Dimakis. My research focuses on data curation for large language models. I currently work as a research scientist intern at Bespoke Labs.

Before starting the PhD program, I was a software engineer at Microsoft working on: Siphon: Streaming data ingestion with Apache Kafka, and PyTorch - ONNX .

LinkedIn  /  CV  /  Google Scholar  /  Github

profile photo
News Publications

  • Infilling Score: A Pretraining Data Detection Algorithm for Large Language Models

    Negin Raoof, Litu Rout, Giannis Daras, Sujay Sanghavi, Constantine Caramanis, Sanjay Shakkottai, Alex Dimakis

    ICLR 2025 Paper

  • Modeling Bilingual Disfluencies with Large Language Models

    Negin Raoof, Yating Wu, Carlos Bonilla, Junyi Jessy Li, Stephanie M Grasso, Alex Dimakis, Zoi Gkalitsiou

    ICML 2024 Workshop on LLMs and Cognition Paper

  • Solving Inverse Problems Provably via Posterior Sampling with Latent Diffusion Models

    Litu Rout, Negin Raoof, Giannis Daras, Constantine Caramanis, Alexandros G. Dimakis, Sanjay Shakkottai

    NeurIPS 2023 Paper

  • Multitasking Models are Robust to Structural Failure: A Neural Model for Bilingual Cognitive Reserve

    Giannis Daras (*) , Negin Raoof (*), Zoi Gkalitsiou, Alexandros G. Dimakis

    NeurIPS 2022 Paper

Blog Posts