mcgill-nlp Goto Github PK

adversarialtriggers

Code for "Universal Adversarial Triggers Are Not Universal."

aurora

Code and data for the paper: Learning Action and Reasoning-Centric Image Editing from Videos and Simulation

barbados-workshop-2024

bias-bench

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

contextual-nmn

diffusers

🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch

diffusion-itm

Code and data setup for the paper "Are Diffusion Models Vision-and-language Reasoners?"

faithdial

feedbackqa

FeedbackQA: Improving Question Answering Post-Deployment with Interactive Feedback

imagecode

Code and data for ImageCoDe, a contextual vison-and-language benchmark

instruct-qa

Code and Data for "Evaluating Correctness and Faithfulness of Instruction-Following Models for Question Answering"

latent-translation

Code for the paper "Modelling Latent Translations for Cross-Lingual Transfer"

length-generalization

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

llm2vec

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

logicalknowedit

magnifico

mcgill-nlp.github.io

medal

Large medical text dataset curated for abbreviation disambiguation, designed for natural language understanding pre-training in the medical domain

mkdocs-template

Template for creating project docs with mkdocs-material

mlquestions

polytropon

project-page-template

Template for creating project webpages based on jekyll/minimal-mistakes

retriever-lm-reasoning

Code for "Can Retriever-Augmented Language Models Reason? The Blame Game Between the Retriever and the Language Model", EMNLP Findings 2023

scope-ambiguity

Code and data for the paper 'Scope Ambiguities in Large Language Models'.

starcodersafetyeval

Code for safety evaluations of StarCoder.

statcan-dialogue-dataset

The StatCan Dialogue Dataset: Retrieving Data Tables through Conversations with Genuine Intents

syntactic-substitutability

topiocqa

Code and data for reproducing baselines for TopiOCQA, an open-domain conversational question-answering dataset

ud-to-meaning

A repository for code related to a project mapping Universal Dependencies syntactic forms to meaning representations.

vision-language-models-are-bows

Experiments and data for the paper "When and why vision-language models behave like bags-of-words, and what to do about it?" Oral @ ICLR 2023