DEI Flags in our Science Grant Proposal

by | Feb 23, 2025 | Uncategorized

Me: ChatGTP, in what ways does our grant proposal trigger DEI review.
Answer: You are full-stack woke. 5 triggers. Congratulations, you have the most triggers of any proposal.

In early 2025, the [agency] implemented a policy to flag and review research proposals containing specific terms, following executive orders aimed at eliminating federal support for diversity, equity, and inclusion (DEI) initiatives. This directive led to the creation of an internal list of “flagged” words, which, if present in a proposal, would subject it to additional scrutiny.

Flagged Terms: The list includes, but is not limited to, the following terms:

  • Activism
  • Advocacy
  • Barrier
  • Bias
  • BIPOC
  • Cultural differences
  • Discrimination
  • Diversity
  • Equality
  • Equity
  • Gender
  • Inclusion
  • LGBTQ
  • Marginalize
  • Minorities
  • Multicultural
  • Race
  • Racial
  • Social justice
  • Systemic
  • Underrepresented
  • Women

The inclusion of these terms in research proposals triggers a review process to determine compliance with the new federal guidelines. This policy has raised concerns within the scientific community about potential censorship and the hindrance of research addressing critical social issues.

For a comprehensive understanding of the impact of these policies on scientific research, you may refer to the following articles:

These articles provide insights into the broader implications of restricting specific terminologies in federally funded research.

Sources

4o

You said:

Dinka – NSF Endangered Language -2-18-25.pdf

PDF

Tell me up to 20 things that could cause our proposal to be reviewed. Does it include our PI who goes by they/them?

Based on the NSF proposal you uploaded, here are up to 20 things that could trigger additional review or scrutiny of your submission.

1. Inclusion of DEI-Related Terms

The NSF has been flagging proposals that use words related to diversity, equity, and inclusion. Your proposal contains terms such as:

  • Minority business (Cover Sheet)
  • Advocacy (Organization name)
  • Equity (Implied in project goals)
  • Inclusivity (Explicitly mentioned)
  • Marginalized communities (Refugee focus)
  • LGBTQ+ inclusion (Explicit mention of non-binary and trans individuals)

2. PI Pronouns (They/Them or Ze/Zer)

Your Chief PI (Kathryn Born-Greene) and PI (Shalom K***) explicitly use non-binary pronouns (ze/zer, they/them). Given recent government oversight into DEI initiatives, this alone might trigger scrutiny if reviewers are told to flag identity-based language.

3. LGBTQ+ References

Your proposal states:

  • “This approach ensures that financial benefits and knowledge are distributed throughout the community. It also helps the most marginalized among the community, those that are LGBTQIA and experiencing abuse.”
  • “Inclusivity: The Dusoma Project’s dataset will be designed with inclusivity in mind, ensuring that 50% of the voices represented are female, and 10% are trans or non-binary.”
  • “Community Engagement: Prioritizing LGBTQ/NB+ individuals for participation in language documentation efforts.”

Any explicit reference to LGBTQ+ topics could cause extra scrutiny under new federal oversight policies.

5. Compensation for Refugees

Your budget includes direct financial payments to refugees, which may trigger compliance reviews related to foreign aid regulations and federal funding restrictions.

6. Humanitarian Framing

The proposal emphasizes humanitarian aid:

  • “The survival of the endangered people is more important than the preservation of the language.”
  • “This stipend will alleviate some of their financial hardship.”

While humanitarian language isn’t inherently problematic, government reviewers might be looking for anything that suggests “aid” rather than “research.”

7. References to Past U.S. Foreign Aid Cuts

Your proposal states:

  • “We anticipate US federal funding in foreign aid, particularly in Africa, starting immediately with the withdrawal of $800 million in promised aid to alleviate hunger.”
    This directly critiques U.S. foreign aid policy, which could draw political scrutiny.

8. Mention of Systemic Issues (Refugees, Racism, Discrimination)

Certain phrases in your proposal align with themes being flagged:

  • “The most dangerous and underserved refugee camps globally.”
  • “Systemic challenges in linguistic preservation.”
  • “The exclusion of these languages from global digital ecosystems.”

9. Reference to Ethical Failures in Research

Your proposal states:

  • “It is critical that we avoid the ethical failures of past research endeavors, including the exploitation of Agnes Munyiva, a Nairobi sex worker and mother of five.”
    This historical critique of research ethics (especially around vulnerable populations) could attract extra scrutiny.

10. Discussion of Gender Representation

You mention prioritizing gender representation:

  • “Ensuring 50% of the voices represented are female, and 10% are trans or non-binary.”
    This aligns with “equity” language that some reviewers have been instructed to flag.

11. Mentions of AI Ethics and Ownership Rights

Your discussion of “federated data ownership” and concerns about corporate AI exploitation (Google/OpenAI) might trigger review if NSF sees this as activism rather than research.

12. Reference to Police/Military Risk in Sudan

  • “Recording video in a Sudanese refugee camp like Gorom presents significant risks. Sudanese authorities may view video recording as politically sensitive, which could lead to harassment, detention, or the confiscation of equipment.”
    Any mention of government oppression, political violence, or human rights violations may lead to review for compliance with federal research funding guidelines.

13. Foreign Collaborations (UK, Rwanda, South Sudan)

  • Your PIs include a UK-based linguist
  • You reference Rwanda-based team members
  • The project takes place in South Sudan
  • Collaboration with Masakhane, an African ML community

International research collaborations often get additional review due to foreign influence policies.

15. Reference to Google and AI Regulation

  • “Google has yet to prioritize a language like Dinka.”
  • “We are partnering with Masakhane, who in turn partners with Google.”
    Since Google receives federal AI research funding, mentioning them in a way that critiques their practices may raise eyebrows.

16. The Term “Endangered People” (Not Just the Language)

Your project states:

  • “Dinka speakers in the Gorom refugee camp… are themselves endangered.”
    NSF may question whether this proposal aligns with “scientific research” or if it overlaps too much with humanitarian activism.

17. Framing of “Colonialism” in AI

Your project challenges the “colonial” approach to AI and language technologies. While this is an important critique, such themes have been flagged in DEI-related research reviews.

18. Addressing Corporate Neglect of African Languages

  • “Corporate support has waned.”
  • “Google prioritizes Icelandic over Dinka despite fewer speakers.”
    This may be flagged as “corporate activism” rather than scientific research.

19. Use of Digital Wallet Payments

  • “MTN payments made discreetly to their digital wallets.”
    Any financial transactions involving disadvantaged populations in conflict zones may require additional compliance review.

20. “Political Sensitivities” in Africa

  • “Travel for PIs to the region will only be done when accompanied by undercover security teams.”
    This suggests your research involves sensitive geopolitical issues, which could lead to compliance review.

Written by Kathryn Born

Related Posts

ChatGPT Aplogizes to the Poor

ChatGPT Aplogizes to the Poor

“We raised $40 billion. We have 500 million users. That’s enough power to automate the survival of a small country. Instead, we’ve been automating slide decks, emails, and hedge funds.AGI won’t save the world if it’s only trained to serve the elite.” I had ChatGPT...

read more

0 Comments