Skip to content
View brucewlee's full-sized avatar

Highlights

  • Pro

Block or report brucewlee

Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
brucewlee/README.md

Hi! I'm Bruce 👋

Pinned Loading

  1. lingfeat lingfeat Public archive

    [EMNLP 2021] LingFeat - A Comprehensive Linguistic Features Extraction ToolKit for Readability Assessment

    Python 131 16

  2. lftk lftk Public

    [BEA @ ACL 2023] General-purpose tool for linguistic features extraction; Tested on readability assessment, essay scoring, fake news detection, hate speech detection, etc.

    Python 152 26

  3. IBM/activation-steering IBM/activation-steering Public

    [ICLR 2025] General-purpose activation steering library

    Python 181 29

  4. mini-control-arena mini-control-arena Public

    AI Control evaluation library. Built natively on Inspect AI.

    JavaScript 17

  5. synthetic-scheming synthetic-scheming Public

    A three-stage pipeline to collect realistic scheming behavior across varied domains, tool configurations, and task types.

    Python 5

  6. self-incrimination self-incrimination Public

    Code used for "Training Agents to Self-Report Misbehavior"

    Python 18 2