Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Skip to content

About Data and Codes for EMNLP 2023 System Demo Paper "QACHECK: A Demonstration System for Question-Guided Multi-Hop Fact-Checking"

License

Notifications You must be signed in to change notification settings

XinyuanLu00/QACheck

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

10 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

QACheck

Data and Codes for "QACHECK: A Demonstration System for Question-Guided Multi-Hop Fact-Checking" (EMNLP 2023, System Demonstrations).

System Overview

We introduce the Question-guided Multi-hop Fact-Checking (QACheck) system, which provides an explainable fact-checking process by asking and answering a series of relevant questions.

The general framework of QACheck

  • Claim Verifier $\mathcal{D}$: determine the sufficiency of the existing context to validate the claim, i.e., $\mathcal{D}(c, C) \rightarrow {\text{True}, \text{False}}$.

  • Question Generator $\mathcal{Q}$: generate the next question that is necessary for verifying the claim, i.e., $Q(c, C) \rightarrow q$.

  • Question-Answering Model $\mathcal{A}$: answer the question and provide the supported evidence, i.e., $\mathcal{A}(q) \rightarrow a, e$.

  • Validator $\mathcal{V}$: validate the usefulness of the newly-generated (Q, A) pair based on the existing context and the claim, i.e., $\mathcal{V}(c, {q, a}, C) \rightarrow {\text{True}, \text{False}}$.

  • Reasoner $\mathcal{R}$: utilize the relevant context to justify the veracity of the claim and outputs the final label, i.e., $\mathcal{R}(c, C) \rightarrow {\text{Supported}, \text{Refuted}}$.

Demo System

Clone the github to your local machine and install the required packages.

pip install flask
pip install openai
pip install backoff

Run the demo system.

python run-demo.py \
    --model_name <gpt-4 or gpt-3.5-turbo> \
    --API_KEY <Your OpenAI API key> \

Reference

Please cite the paper in the following format if you use this dataset during your research.

@inproceedings{PanQACheck23,
  author       = {Liangming Pan, Xinyuan Lu, Min-Yen Kan, Preslav Nakov},
  title        = {QACHECK: A Demonstration System for Question-Guided Multi-Hop Fact-Checking},
  booktitle    = {Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing System Demonstrations Track (EMNLP 2023 Demo Track)},
  address      = {Singapore},
  year         = {2023},
  month        = {Dec}
}

Q&A

If you encounter any problem, please either directly contact the Liangming Pan or leave an issue in the github repo.

About

About Data and Codes for EMNLP 2023 System Demo Paper "QACHECK: A Demonstration System for Question-Guided Multi-Hop Fact-Checking"

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published