publications

publications by categories in reversed chronological order. generated by jekyll-scholar.

2026

  1. NeurIPS
    PrivacySIM: Evaluating LLM Simulation of User Privacy Behavior
    James Flemings, and Murali Annavaram
    Proceedings of Neural Information Processing Systems Track on Evaluations and Datasets, 2026
    arXiv Code
  2. PETS
    Personalizing Agent Privacy Decisions via Logical Entailment
    James Flemings, Ren Yi , Octavian Suciu , Kassem Fawaz , Murali Annavaram , and Marco Gruteser
    Proceedings of Privacy Enhancing Technologies, 2026
    arXiv
  3. ICLR
    Hubble: a Model Suite to Advance the Study of LLM Memorization
    Johnny Tian-Zheng Wei , Ameya Godbole , Mohammad Aflah Khan , Ryan Wang , Xiaoyuan Zhu , James Flemings, Nitya Kashyap , Krishna P Gummadi , Willie Neiswanger , and Robin Jia
    Proceedings of International Conference on Learning Representations, 2026
    arXiv Code
  4. TMLR
    Memory-Efficient Differentially Private Training with Gradient Random Projection
    Alex Mulrooney , Devansh Gupta , James Flemings, Huanyu Zhang , Murali Annavaram , Meisam Razaviyayn , and Xinwei Zhang
    Transactions on Machine Learning Research, 2026
    arXiv

2025

  1. EMNLP
    TokenSmith: Streamlining Data Editing, Search, and Inspection for Large-Scale Language Model Training and Interpretability
    Mohammad Aflah Khan , Ameya Godbole , Johnny Tian-Zheng Wei , Ryan Wang , James Flemings, Krishna P Gummadi , Willie Neiswanger , and Robin Jia
    In Proceedings of EMNLP: System Demonstrations, 2025
    arXiv Code
  2. preprint
    Differentially Private In-context Learning via Sampling Few-shot Mixed with Zero-shot Outputs
    James Flemings, HaoSheng Gan , Hongyi Li , Meisam Razaviyayn , and Murali Annavaram
    arxiv preprint, 2025
    arXiv
  3. ACL
    Estimating Privacy Leakage of Augmented Contextual Knowledge in Language Models
    James Flemings, Bo Jiang , Wanrong Zhang , Zafar Takhirov , and Murali Annavaram
    In Proceedings of ACL, 2025
    arXiv Code

2024

  1. ACL
    Differentially Private Knowledge Distillation via Synthetic Text Generation
    James Flemings, and Murali Annavaram
    In Findings of ACL, 2024
    arXiv Code
  2. NAACL
    Differentially Private Next-Token Prediction of Large Language Models
    James Flemings, Meisam Razaviyayn , and Murali Annavaram
    In Proceedings of NAACL, 2024
    arXiv Code
  3. preprint
    Adaptively private next-token prediction of large language models
    James Flemings, Meisam Razaviyayn , and Murali Annavaram
    arxiv preprint, 2024
    arXiv