Skip to content
@socialfoundations

Social Foundations of Computation

Max Planck Institute for Intelligent Systems, Tübingen

Popular repositories Loading

  1. whynot whynot Public

    A Python sandbox for decision making in dynamics

    Python 418 43

  2. folktables folktables Public

    Datasets derived from US census data

    Python 241 18

  3. tttlm tttlm Public

    Test-time-training on nearest neighbors for large language models

    Python 28 4

  4. error-parity error-parity Public

    Achieve error-rate fairness between societal groups for any score-based classifier.

    Python 16 4

  5. benchbench benchbench Public

    BenchBench is a Python package to evaluate multi-task benchmarks.

    Python 13 1

  6. lawma lawma Public

    Lawma: A lightly fine-tuned Llama model for legal classification tasks.

    Jupyter Notebook 13

Repositories

Showing 10 of 12 repositories
  • folktexts Public

    Get classification risk scores on tabular tasks using LLMs

    socialfoundations/folktexts’s past year of commit activity
    Jupyter Notebook 11 MIT 0 0 0 Updated Nov 21, 2024
  • causal-features Public Forked from mlfoundations/tableshift

    Code to reproduce the paper "Do causal predictors generalize better to new domains?"

    socialfoundations/causal-features’s past year of commit activity
    Python 7 7 0 0 Updated Oct 23, 2024
  • surveying-language-models Public

    Code to reproduce the paper "Questioning the Survey Responses of Large Language Models"

    socialfoundations/surveying-language-models’s past year of commit activity
    Jupyter Notebook 7 MIT 1 0 0 Updated Sep 23, 2024
  • lm-evaluation-harness Public Forked from EleutherAI/lm-evaluation-harness

    A framework for few-shot evaluation of language models.

    socialfoundations/lm-evaluation-harness’s past year of commit activity
    Python 1 MIT 1,912 0 0 Updated Sep 20, 2024
  • lawma Public

    Lawma: A lightly fine-tuned Llama model for legal classification tasks.

    socialfoundations/lawma’s past year of commit activity
    Jupyter Notebook 13 0 0 0 Updated Sep 14, 2024
  • benchbench Public

    BenchBench is a Python package to evaluate multi-task benchmarks.

    socialfoundations/benchbench’s past year of commit activity
    Python 13 MIT 1 0 0 Updated Jul 18, 2024
  • training-on-the-test-task Public

    Code to reproduce the experiments in the paper Training on the Test Task Confounds Evaluation and Emergence.

    socialfoundations/training-on-the-test-task’s past year of commit activity
    Jupyter Notebook 7 0 0 0 Updated Jul 14, 2024
  • folktables Public

    Datasets derived from US census data

    socialfoundations/folktables’s past year of commit activity
    Python 241 MIT 18 5 3 Updated May 15, 2024
  • error-parity Public

    Achieve error-rate fairness between societal groups for any score-based classifier.

    socialfoundations/error-parity’s past year of commit activity
    Python 16 MIT 4 0 1 Updated Apr 26, 2024
  • tttlm Public

    Test-time-training on nearest neighbors for large language models

    socialfoundations/tttlm’s past year of commit activity
    Python 28 MIT 4 0 0 Updated Apr 18, 2024
View all repositories

Most used topics

Loading…