Skip to content

@socialfoundations Social Foundations of Computation

Change the repository type filter

All

    Repositories list

    13 repositories

    • folktexts

      Public
      Evaluate uncertainty, calibration, accuracy, and fairness of LLMs on real-world survey data!
      pythonmachine-learningtabular-datatransformersuncertaintyfairnesslarge-language-models
      Jupyter Notebook
      •
      MIT License
      •1•17•1•1•Updated Feb 12, 2025Feb 12, 2025

    • causal-features

      Public
      Code to reproduce the paper "Do causal predictors generalize better to new domains?"
      Python
      •
      Other
      •9•8•0•0•Updated Feb 7, 2025Feb 7, 2025

    • twitter-predictability

      Public
      Jupyter Notebook
      •
      MIT License
      •0•0•0•0•Updated Jan 22, 2025Jan 22, 2025

    • surveying-language-models

      Public
      Code to reproduce the paper "Questioning the Survey Responses of Large Language Models"
      Jupyter Notebook
      •
      MIT License
      •1•7•0•0•Updated Dec 8, 2024Dec 8, 2024

    • training-on-the-test-task

      Public
      Code to reproduce the experiments in the paper Training on the Test Task Confounds Evaluation and Emergence.
      Jupyter Notebook
      •1•9•0•0•Updated Dec 3, 2024Dec 3, 2024

    • lm-evaluation-harness

      Public
      A framework for few-shot evaluation of language models.
      Python
      •
      MIT License
      •2.1k•1•0•0•Updated Sep 20, 2024Sep 20, 2024

    • lawma

      Public
      Lawma: A lightly fine-tuned Llama model for legal classification tasks.
      language-modellegaltechlegaltools
      Jupyter Notebook
      •0•17•0•0•Updated Sep 14, 2024Sep 14, 2024

    • benchbench

      Public
      BenchBench is a Python package to evaluate multi-task benchmarks.
      Python
      •
      MIT License
      •1•13•0•0•Updated Jul 18, 2024Jul 18, 2024

    • folktables

      Public
      Datasets derived from US census data
      Python
      •
      MIT License
      •20•250•7•4•Updated May 15, 2024May 15, 2024

    • error-parity

      Public
      Achieve error-rate fairness between societal groups for any score-based classifier.
      Python
      •
      MIT License
      •4•16•0•1•Updated Apr 26, 2024Apr 26, 2024

    • tttlm

      Public
      Test-time-training on nearest neighbors for large language models
      Python
      •
      MIT License
      •5•37•0•0•Updated Apr 18, 2024Apr 18, 2024

    • backward_baselines

      Public
      Code for "Is your model predicting the past?"
      Jupyter Notebook
      •
      MIT License
      •0•1•0•0•Updated Mar 10, 2024Mar 10, 2024

    • whynot

      Public
      A Python sandbox for decision making in dynamics
      Python
      •
      MIT License
      •43•420•8•2•Updated Aug 21, 2023Aug 21, 2023