Skip to content
@BatsResearch

Bats Research

We are a machine learning research group at Brown University. We work on improving the processes by which humans teach and instruct computers.

Pinned Loading

  1. bonito bonito Public

    A lightweight library for generating synthetic instruction tuning datasets for your data without GPT.

    Python 702 46

  2. alfred alfred Public

    A system for prompted weak supervision. Alfred is a powerful tool that leverages large language models to accelerate data annotation.

    Python 50 6

  3. csp csp Public

    Learning to compose soft prompts for compositional zero-shot learning.

    Python 84 5

  4. zsl-kg zsl-kg Public

    Framework for zero-shot learning with knowledge graphs.

    Python 112 8

Repositories

Showing 10 of 28 repositories
  • menghini-neurips23-code Public

    Exploring prompt tuning with pseudolabels for multiple modalities, learning settings, and training strategies.

    BatsResearch/menghini-neurips23-code’s past year of commit activity
    Python 44 2 0 0 Updated Nov 8, 2024
  • planetarium Public

    Dataset and benchmark for assessing LLMs in translating natural language descriptions of planning problems into PDDL

    BatsResearch/planetarium’s past year of commit activity
    Python 43 BSD-3-Clause 4 1 0 Updated Oct 16, 2024
  • alfred Public

    A system for prompted weak supervision. Alfred is a powerful tool that leverages large language models to accelerate data annotation.

    BatsResearch/alfred’s past year of commit activity
    Python 50 BSD-3-Clause 6 1 0 Updated Oct 10, 2024
  • cross-lingual-detox Public

    Code for "Preference Tuning For Toxicity Mitigation Generalizes Across Languages." Paper accepted at Findings of EMNLP 2024

    BatsResearch/cross-lingual-detox’s past year of commit activity
    Jupyter Notebook 15 BSD-3-Clause 0 0 0 Updated Oct 4, 2024
  • LexC-Gen-Data-Archive Public

    Data Repository for LexC-Gen: Generating Data for Extremely Low-Resource Languages with Large Language Models and Bilingual Lexicons

    BatsResearch/LexC-Gen-Data-Archive’s past year of commit activity
    1 1 0 0 Updated Oct 3, 2024
  • LexC-Gen Public

    Generate synthetic labeled data for extremely low-resource languages using bilingual lexicons.

    BatsResearch/LexC-Gen’s past year of commit activity
    Python 13 4 0 0 Updated Oct 3, 2024
  • bonito Public

    A lightweight library for generating synthetic instruction tuning datasets for your data without GPT.

    BatsResearch/bonito’s past year of commit activity
    Python 702 BSD-3-Clause 46 2 1 Updated Sep 12, 2024
  • BatsResearch/nayak-aclfindings24-code’s past year of commit activity
    Python 19 1 1 0 Updated Jul 16, 2024
  • nplm Public

    A weak supervision framework for (partial) labeling functions

    BatsResearch/nplm’s past year of commit activity
    Python 14 BSD-3-Clause 3 0 0 Updated Jul 15, 2024
  • labelmodels Public

    Lightweight implementations of generative label models for weakly supervised machine learning

    BatsResearch/labelmodels’s past year of commit activity
    Python 18 Apache-2.0 4 1 1 Updated Apr 10, 2024