Skip to content

@McGill-NLP McGill NLP

Change the repository type filter

All

    Repositories list

    50 repositories

    • mcgill-nlp.github.io

      Public
      Python
      •23•0•15•2•Updated Sep 5, 2025Sep 5, 2025

    • mSTEB

      Public
      Jupyter Notebook
      •0•0•0•0•Updated Aug 25, 2025Aug 25, 2025

    • bias-bench

      Public
      ACL 2022: An Empirical Survey of the Effectiveness of Debiasing Techniques for Pre-trained Language Models.
      Python
      •41•145•0•0•Updated Aug 18, 2025Aug 18, 2025

    • AdversarialTriggers

      Public
      TACL 2025: Investigating Adversarial Trigger Transfer in Large Language Models
      Python
      •
      MIT License
      •2•18•0•0•Updated Aug 17, 2025Aug 17, 2025

    • agent-reward-bench

      Public
      AgentRewardBench: Evaluating Automatic Evaluations of Web Agent Trajectories
      Python
      •1•37•0•0•Updated Aug 7, 2025Aug 7, 2025

    • meaning-change

      Public
      R
      •
      MIT License
      •0•1•0•0•Updated Jul 30, 2025Jul 30, 2025

    • AfroBench

      Public
      Large Scale Benchmark of Large Language Models on African Languages
      Python
      •2•9•0•0•Updated Jul 28, 2025Jul 28, 2025

    • unequal-unlearning

      Public
      Python
      •0•5•2•0•Updated Jul 15, 2025Jul 15, 2025

    • nano-aha-moment

      Public
      Single File, Single GPU, From Scratch, Efficient, Full Parameter Tuning library for "RL for LLMs"
      Jupyter Notebook
      •
      MIT License
      •47•523•4•1•Updated Jul 7, 2025Jul 7, 2025

    • AURORA

      Public
      Code and data for the paper: Learning Action and Reasoning-Centric Image Editing from Videos and Simulation
      Python
      •
      MIT License
      •2•30•0•0•Updated Jun 30, 2025Jun 30, 2025

    • ast-lrl-speech

      Public
      Python
      •0•0•0•0•Updated Jun 22, 2025Jun 22, 2025

    • VinePPO

      Public
      Code for the paper "VinePPO: Unlocking RL Potential For LLM Reasoning Through Refined Credit Assignment"
      Python
      •
      MIT License
      •20•169•4•0•Updated May 25, 2025May 25, 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"
      Apache License 2.0
      •0•0•0•0•Updated May 14, 2025May 14, 2025

    • thoughtology

      Public
      MIT License
      •2•10•0•0•Updated May 12, 2025May 12, 2025

    • constituent-movement

      Public
      Repo for "Language Models Largely Exhibit Human-like Constituent Ordering Preferences"
      Python
      •1•2•0•0•Updated Apr 26, 2025Apr 26, 2025

    • weblinx-browsergym

      Public
      Python
      •3•1•0•1•Updated Apr 25, 2025Apr 25, 2025

    • safearena

      Public
      SafeArena is a benchmark for assessing the harmful capabilities of web agents
      Python
      •3•17•2•0•Updated Apr 23, 2025Apr 23, 2025

    • malicious-ir

      Public
      Code for `Exploiting Instruction-Following Retrievers for Malicious Information Retrieval`
      retrievalsafetyinstruction-following-retrievalmalicious-retrieval
      Python
      •
      MIT License
      •1•6•0•0•Updated Apr 1, 2025Apr 1, 2025

    • project-page-template

      Public template
      Template for creating project webpages based on jekyll/minimal-mistakes
      1•1•0•0•Updated Mar 13, 2025Mar 13, 2025

    • tiny-aha-moment-length-budget

      Public
      Python
      •47•0•0•0•Updated Mar 11, 2025Mar 11, 2025

    • CHASE

      Public
      Synthetic Data Generation for Evaluation
      Python
      •
      MIT License
      •4•14•0•0•Updated Feb 21, 2025Feb 21, 2025

    • Injongo

      Public
      A multicultural, open-source benchmark dataset for 16 African languages with utterances generated by native speakers across diverse domains.
      Jupyter Notebook
      •
      GNU General Public License v3.0
      •0•0•0•0•Updated Feb 12, 2025Feb 12, 2025

    • weblinx

      Public
      WebLINX is a benchmark for building web navigation agents with conversational capabilities
      nlpagentwebcomputer-visionnavigationagentsmultimodalllm
      Python
      •
      Apache License 2.0
      •17•157•0•0•Updated Feb 11, 2025Feb 11, 2025

    • llm2vec

      Public
      Code for 'LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders'
      Python
      •
      MIT License
      •128•1.6k•36•4•Updated Jan 24, 2025Jan 24, 2025

    • webllama

      Public
      Llama-3 agents that can browse the web by following instructions and talking to you
      Python
      •
      MIT License
      •108•1.4k•2•0•Updated Dec 10, 2024Dec 10, 2024

    • statcan-dialogue-dataset

      Public
      The StatCan Dialogue Dataset: Retrieving Data Tables through Conversations with Genuine Intents
      Python
      •2•9•0•0•Updated Nov 6, 2024Nov 6, 2024

    • incontext-code-generation

      Public
      NAACL 2024: Evaluating In-Context Learning of Libraries for Code Generation
      Python
      •2•9•0•0•Updated Oct 23, 2024Oct 23, 2024

    • instruct-qa

      Public
      Code and Data for "Evaluating Correctness and Faithfulness of Instruction-Following Models for Question Answering"
      Python
      •
      Apache License 2.0
      •5•86•5•1•Updated Aug 12, 2024Aug 12, 2024

    • scope-ambiguity

      Public
      Code and data for the paper 'Scope Ambiguities in Large Language Models'.
      Python
      •
      MIT License
      •2•5•0•0•Updated Jun 25, 2024Jun 25, 2024

    • length-generalization

      Public
      Code for the paper "The Impact of Positional Encoding on Length Generalization in Transformers", NeurIPS 2023
      Python
      •
      MIT License
      •7•137•3•0•Updated Apr 30, 2024Apr 30, 2024