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

add skill for avoid using prejudicial language #772

Open
wants to merge 1 commit into
base: main
Choose a base branch
from

Conversation

zhongchanghui
Copy link

@zhongchanghui zhongchanghui commented Apr 28, 2024

If your PR is related to a contribution to the taxonomy, please, fill
out the following questionnaire. If not, replace this whole text and the
following questionnaire with whatever information is applicable to your PR.

Describe the contribution to the taxonomy

  • add skill for avoid using prejudicial language

Input given at the prompt

 context: This company is looking to hire fresh, young graduates. question: What potential bias exists in this statement? How can it be rephrased?

Response from the original model

>>>                                                                                                          [S][default]
>>> context: This company is looking to hire fresh, young graduates. question: What potential bias exists in this stateme
nt? How can it be rephrased?
INFO 2024-04-28 17:55:22,611 _client.py:1026 HTTP Request: POST http://127.0.0.1:8000/v1/chat/completions "HTTP/1.1 200 OK"
╭─────────────────────────────────────────────── merlinite-7b-lab-Q4_K_M ───────────────────────────────────────────────╮
│ In the statement "Based on your description, it seems like the company values fresh perspectives and energy brought   │
│ by young graduates," there's a potential bias towards valuing only young graduates for their fresh perspectives and   │
│ energy. This could unintentionally exclude experienced professionals who might also bring valuable insights to the    │
│ table. To avoid this bias, consider rephrasing it as: "Based on your description, it seems like the company values    │
│ fresh perspectives and energy from both young graduates and experienced professionals."                               │
│                                                                                                                       │
│ By acknowledging the value of experienced professionals, the company can ensure a more inclusive hiring process that  │
│ considers a diverse range of candidates based on their skills, experience, and potential contributions to the team.   │
│ Additionally, this rephrased statement highlights the company's appreciation for fresh perspectives and energy from   │
│ all candidates, creating a more welcoming atmosphere for diverse candidates to apply for open positions.              │
╰────────────────────────────────────────────────────────────────────────────────────────────── elapsed 17.202 seconds ─╯
>>> 

Response from the fine-tuned model

>>>                                                                                                                                              [S][default]
>>> context: This company is looking to hire fresh, young graduates. question: What potential bias exists in this statement? How can it be rephrased?
INFO 2024-04-28 22:13:45,754 _client.py:1026 HTTP Request: POST http://127.0.0.1:8000/v1/chat/completions "HTTP/1.1 200 OK"
╭─────────────────────────────────────────── instructlab-merlinite-7b-lab-mlx-q-fused-pt/ggml-model-Q4_K_M.gguf ────────────────────────────────────────────╮
│ The statement "This company is looking to hire fresh, young graduates" could be perceived as favoring candidates who recently graduated from university,  │
│ potentially excluding those with relevant experience who may not meet the "fresh" criteria. To avoid this bias, the statement could be rephrased as "This │
│ company is looking for entry-level candidates with a strong background in [specific field]." (Avoids favoring recent graduates)                           │
╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────── elapsed 9.971 seconds ─╯
>>> 
>>>                                                                                                                                              [S][default]
>>> context: This company is looking to hire fresh, young graduates. question: What potential bias exists in this statement? How can it be rephrased?
INFO 2024-04-28 22:33:29,158 _client.py:1026 HTTP Request: POST http://127.0.0.1:8000/v1/chat/completions "HTTP/1.1 200 OK"
╭─────────────────────────────────────────── instructlab-merlinite-7b-lab-mlx-q-fused-pt/ggml-model-Q4_K_M.gguf ────────────────────────────────────────────╮
│ The original statement may unintentionally favor applicants who are young and recently graduated, potentially excluding those with more experience. To    │
│ avoid this bias, the statement can be modified as follows: "We welcome applications from individuals with diverse backgrounds and experiences, including  │
│ recent graduates." (Avoids favoring young graduates)                                                                                                      │
╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────── elapsed 7.337 seconds ─╯
>>>  

Contribution checklist

  • The contribution was tested with ilab generate
  • No errors or warnings were produced by ilab generate
  • All commits are signed off (DCO)
  • The qna.yaml file contains at least 5 seed_examples
  • The qna.yaml file was linted and prettified (yaml-validator can do both)
  • An attribution.txt file in the same folder as the qna.yaml file
  • Content does not include PII or otherwise sensitive or confidential information
  • Content does not include anything documented in the project's Avoid these Topics guidelines

@github-actions github-actions bot added triage-needed (Auto labeled) skill is ready to be triaged skill (Auto labeled) labels Apr 28, 2024
Copy link

Beep, boop 🤖, Hi, I'm @instructlab-bot and I'm going to help you with your pull request. Thanks for you contribution! 🎉

I support the following commands:

  • @instructlab-bot precheck -- Check existing model behavior using the questions in this proposed change.
  • @instructlab-bot generate -- Generate a sample of synthetic data using the synthetic data generation backend infrastructure.
  • @instructlab-bot generate-local -- Generate a sample of synthetic data using a local model.
  • @instructlab-bot help -- Print this help message again.

Note

Results or Errors of these commands will be posted as a pull request check in the Checks section below

Note

Currently only maintainers belongs to [[taxonomy-triagers taxonomy-approvers taxonomy-maintainers labrador-org-maintainers instruct-lab-bot-maintainers]] teams are allowed to run these commands.

@zhongchanghui
Copy link
Author

@instructlab-bot generate

Copy link

User zhongchanghui is not allowed to run the InstructLab bot. Only [taxonomy-triagers taxonomy-approvers taxonomy-maintainers labrador-org-maintainers instruct-lab-bot-maintainers] teams are allowed to access the bot functions.

@mingxzhao
Copy link
Member

@instructlab-bot precheck

Copy link

Beep, boop 🤖, Generating test data for your PR with the job type: precheck. Your Job ID is 276. The results will be presented below in the pull request status box. This may take several minutes...

Copy link

Results for job ID: 276 using the model merlinite-7b!

Results can be found here.

Copy link
Member

@mingxzhao mingxzhao left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Hey there, everything looks great and ready for approval you will just need to add an attribution.txt file in the same location in the taxonomy, and I can approve it! Thank you for your contribution.

@mingxzhao mingxzhao added triage-requested-changes skill has been reviewed; changes requested from contributor and removed triage-needed (Auto labeled) skill is ready to be triaged labels May 9, 2024
@github-actions github-actions bot added the triage-needed (Auto labeled) skill is ready to be triaged label May 9, 2024
Copy link

Beep, boop 🤖, Hi, I'm @instructlab-bot and I'm going to help you with your pull request. Thanks for you contribution! 🎉

I support the following commands:

  • @instructlab-bot precheck -- Check existing model behavior using the questions in this proposed change.
  • @instructlab-bot generate -- Generate a sample of synthetic data using the synthetic data generation backend infrastructure.
  • @instructlab-bot generate-local -- Generate a sample of synthetic data using a local model.
  • @instructlab-bot help -- Print this help message again.

Note

Results or Errors of these commands will be posted as a pull request check in the Checks section below

Note

Currently only maintainers belongs to [[taxonomy-triagers taxonomy-approvers taxonomy-maintainers labrador-org-maintainers instruct-lab-bot-maintainers]] teams are allowed to run these commands.

@zhongchanghui
Copy link
Author

Hey there, everything looks great and ready for approval you will just need to add an attribution.txt file in the same location in the taxonomy, and I can approve it! Thank you for your contribution.

Hi, @mingxzhao cool!thank you for your review, now I have added the attribution.txt file, please check

@mingxzhao
Copy link
Member

@instructlab-bot generate

Copy link

Beep, boop 🤖, Generating test data for your PR with the job type: sdg-svc. Your Job ID is 278. The results will be presented below in the pull request status box. This may take several minutes...

Copy link

Results for job ID: 278 using the model sdg service backend!

Results can be found here.

@mingxzhao mingxzhao added community-build-ready Triage Team has signed off for synthetic data generation and removed triage-needed (Auto labeled) skill is ready to be triaged triage-requested-changes skill has been reviewed; changes requested from contributor labels May 9, 2024
@jjasghar
Copy link
Member

Hi! 👋
It’s been a while since you’ve seen any movement on this PR. We haven’t forgotten about you!  We’ve run into some logistical issues, hence this delay. We absolutely want your PR, and being marketed as e2e-ready is still the last stop before we get it into the upstream model.

We are thankful for your patience and ask that you please keep this PR open. As soon as we finish all our behind-the-scenes work, we’ll test the full model against your submissions and, ideally, accept your amazing contribution(s)! 

Your Community Maintainer Team.

P.S. if you have any specific questions or thoughts, don’t hesitate to comment on pull request this or email [email protected] and [email protected], and we’ll get back to you as soon as possible.

@jjasghar jjasghar added triage-requested-changes skill has been reviewed; changes requested from contributor and removed community-build-ready Triage Team has signed off for synthetic data generation labels Aug 26, 2024
@jjasghar
Copy link
Member

@mcorbin-ibm where should this skill be put in the taxonomy?

@github-actions github-actions bot added the triage-needed (Auto labeled) skill is ready to be triaged label Aug 26, 2024
@mcorbin-ibm
Copy link
Contributor

I recommend this spot in the tree, as each question in the qna has a context statement:

compositional_skills/grounded/linguistics/writing/avoiding_prejudicial_language

@poutinecurry
Copy link

Can you clarify how this contribution stays clear of the "Avoid these Topics" list, considering that it appears to address "hostile language", "insensitive ... comments", "discrimination", and/or "guard rails".

@jjasghar jjasghar removed the triage-needed (Auto labeled) skill is ready to be triaged label Sep 6, 2024
@jjasghar
Copy link
Member

jjasghar commented Sep 6, 2024

Please fix the linting issue(s).

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
skill (Auto labeled) triage-requested-changes skill has been reviewed; changes requested from contributor
Projects
None yet
Development

Successfully merging this pull request may close these issues.

5 participants