Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

reviewer2go - a LLM AI review bot #81

Open
2 tasks
bcmcpher opened this issue Dec 8, 2023 · 0 comments
Open
2 tasks

reviewer2go - a LLM AI review bot #81

bcmcpher opened this issue Dec 8, 2023 · 0 comments

Comments

@bcmcpher
Copy link

bcmcpher commented Dec 8, 2023

Title

reviewer2go

Leaders

Brent McPherson
Kendra Oudyk

Collaborators

No response

Brainhack Global 2023 Event

Brainhack Montreal

Project Description

  • We are working on using a large language model to develop prompts to provide a structured review and parameter extraction of a paper.
  • This can greatly ease the review process by automating parts of method extraction.
  • We are working on extracting the the analysis parameters similar to the COBIDAS, specifically working on the parameters as part of the Carp (2012) paper.
  • We'll be working with LangChain and Ollama to test different prompts and models.

Link to project repository/sources

https://github.com/bcmcpher/reviewer2go

Goals for Brainhack Global

Create a sequence of prompts that can systematically extract model parameters and features from an article to facilitate the review process.

Good first issues

  1. Based on a journal's review process, write a prompt chain to evaluate how ready an article is to publish / how well its analyses are described.

  2. Based on a specific review papers criteria, write

Communication channels

https://github.com/bcmcpher/reviewer2go

Skills

  • Python - Basic
    • LangChain - preferred
  • Git - preferred

Onboarding documentation

No response

What will participants learn?

We'll learn how to interact with different LLMs while building LangChain prompts to extract specific information or otherwise summarize the technical writing of an article.

Data to use

No response

Number of collaborators

more

Credit to collaborators

We'll track contributions and decide what kind of product for the hackathon (or other future work) as we go.

Hopefully, we can get to a small demo for NeuroLibre

Image

Leave this text if you don't have an image yet.

Type

other

Development status

0_concept_no_content

Topic

reproducible_scientific_methods

Tools

other

Programming language

Python

Modalities

other, not_applicable

Git skills

1_commit_push

Anything else?

No response

Things to do after the project is submitted and ready to review.

  • Add a comment below the main post of your issue saying: Hi @brainhackorg/project-monitors my project is ready!
  • Twitter-sized summary of your project pitch.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment