McGill-NLP/FaithDial McGill-NLP/FaithDial

  • Stars
    star
    48
  • Rank 594,835 (Top 12 %)
  • Language
    Python
  • License
    MIT License
  • Created over 2 years ago
  • Updated almost 2 years ago
Twitter logo Share LinkedIn logo Share Facebook logo Share
McGill-NLP/FaithDial
github

McGill-NLP

Reviews

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Repository Details

More Repositories

1

llm2vec

Code for 'LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders'
Python
1,210
star
2

medal

Large medical text dataset curated for abbreviation disambiguation, designed for natural language understanding pre-training in the medical domain
Python
231
star
3

length-generalization

Code for the paper "The Impact of Positional Encoding on Length Generalization in Transformers", NeurIPS 2023
Python
113
star
4

bias-bench

ACL 2022: An Empirical Survey of the Effectiveness of Debiasing Techniques for Pre-trained Language Models.
Python
111
star
5

weblinx

WebLINX is a benchmark for building web navigation agents with conversational capabilities
Python
110
star
6

instruct-qa

Code and Data for "Evaluating Correctness and Faithfulness of Instruction-Following Models for Question Answering"
Python
78
star
7

polytropon

Python
44
star
8

topiocqa

Code and data for reproducing baselines for TopiOCQA, an open-domain conversational question-answering dataset
Python
44
star
9

imagecode

Code and data for ImageCoDe, a contextual vison-and-language benchmark
Python
38
star
10

retriever-lm-reasoning

Code for "Can Retriever-Augmented Language Models Reason? The Blame Game Between the Retriever and the Language Model", EMNLP Findings 2023
Python
27
star
11

diffusion-itm

Code and data setup for the paper "Are Diffusion Models Vision-and-language Reasoners?"
Python
21
star
12

MLQuestions

Python
19
star
13

latent-translation

Code for the paper "Modelling Latent Translations for Cross-Lingual Transfer"
Python
16
star
14

AdversarialTriggers

Code for "Universal Adversarial Triggers Are Not Universal."
Python
14
star
15

feedbackqa

FeedbackQA: Improving Question Answering Post-Deployment with Interactive Feedback
Python
6
star
16

contextual-nmn

1
star
17

VinePPO

Code for the paper "VinePPO: Unlocking RL Potential For LLM Reasoning Through Refined Credit Assignment"
Python
1
star
18

ud-to-meaning

A repository for code related to a project mapping Universal Dependencies syntactic forms to meaning representations.
Python
1
star
19

StarCoderSafetyEval

Code for safety evaluations of StarCoder.
Python
1
star