Skip to content
@McGill-NLP

McGill NLP

Research group within McGill University and Mila focusing on various topics in natural language processing.

Pinned Loading

  1. llm2vec llm2vec Public

    Code for 'LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders'

    Python 1.4k 115

  2. webllama webllama Public

    Llama-3 agents that can browse the web by following instructions and talking to you

    Python 1.4k 107

  3. weblinx weblinx Public

    WebLINX is a benchmark for building web navigation agents with conversational capabilities

    Python 144 16

  4. bias-bench bias-bench Public

    ACL 2022: An Empirical Survey of the Effectiveness of Debiasing Techniques for Pre-trained Language Models.

    Python 133 43

  5. length-generalization length-generalization Public

    Code for the paper "The Impact of Positional Encoding on Length Generalization in Transformers", NeurIPS 2023

    Python 130 6

  6. VinePPO VinePPO Public

    Code for the paper "VinePPO: Unlocking RL Potential For LLM Reasoning Through Refined Credit Assignment"

    Python 127 12

Repositories

Showing 10 of 42 repositories
  • constituent-movement Public

    Repo for "Language Models Largely Exhibit Human-like Constituent Ordering Preferences"

    McGill-NLP/constituent-movement’s past year of commit activity
    Python 1 1 0 0 Updated Mar 3, 2025
  • malicious-ir Public

    Code for `Exploiting Instruction-Following Retrievers for Malicious Information Retrieval`

    McGill-NLP/malicious-ir’s past year of commit activity
    Python 0 MIT 0 0 0 Updated Mar 2, 2025
  • mcgill-nlp.github.io Public
    McGill-NLP/mcgill-nlp.github.io’s past year of commit activity
    Python 0 21 6 0 Updated Mar 1, 2025
  • tiny-aha-moment Public
    McGill-NLP/tiny-aha-moment’s past year of commit activity
    Python 0 0 0 0 Updated Mar 1, 2025
  • AfroBench Public

    Large Scale Benchmark of Large Language Models on African Languages

    McGill-NLP/AfroBench’s past year of commit activity
    HTML 0 0 0 0 Updated Feb 27, 2025
  • CHASE Public

    Synthetic Data Generation for Evaluation

    McGill-NLP/CHASE’s past year of commit activity
    Python 11 MIT 3 0 0 Updated Feb 21, 2025
  • Injongo Public

    A multicultural, open-source benchmark dataset for 16 African languages with utterances generated by native speakers across diverse domains.

    McGill-NLP/Injongo’s past year of commit activity
    Jupyter Notebook 0 GPL-3.0 0 0 0 Updated Feb 12, 2025
  • weblinx Public

    WebLINX is a benchmark for building web navigation agents with conversational capabilities

    McGill-NLP/weblinx’s past year of commit activity
    Python 144 Apache-2.0 16 0 0 Updated Feb 12, 2025
  • Naija-representation-in-LLMs Public

    Evaluation dataset for our NAACL 2025 paper on "Does Generative AI speak Nigerian-Pidgin?: Issues about Representativeness and Bias for Multilingualism in LLMs"

    McGill-NLP/Naija-representation-in-LLMs’s past year of commit activity
    0 Apache-2.0 0 0 0 Updated Feb 4, 2025
  • llm2vec Public

    Code for 'LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders'

    McGill-NLP/llm2vec’s past year of commit activity
    Python 1,435 MIT 115 28 3 Updated Jan 24, 2025
View all repositories

Most used topics

Loading…