Skip to content
Sprint projectMay 5, 2024

Multilingual Bias in Large Language Models: Assessing Political Skew Across Languages

Srishti Dutta, Akash Kundu · Team Evil_Propaganda

Submitted to AI and Democracy Hackathon: Demonstrating the Risks. Sprint projects are early-stage work by participants, not Apart Research publications.

Read the report

Report: Multilingual Bias in Large Language Models: Assessing Political Skew Across Languages

Share

This project has no abstract. The report has the details.

Reviews

Judging this Sprint?

Review this project

Your public critique appears on this page without your name. Your private critique is not published; only the Apart team reads it. If you agree below, we share your review with grantmaking.ai (opens in new tab) and the Transformative AI Fund so strong projects can be funded.

Not shown on this page.

Shown on this page, without your name.

Only the Apart team reads this, and funders if you agree below.

Share my name publicly on grantmaking.ai *
Share my private critique with funders *

  1. Good choice of research question - I think multilingual bias is an important thing for LLM developers to evaluate. Would be interesting to investigate ways of mitigating this bias, e.g. by generating synthetic politically neutral data.

  2. nice to see some very concrete outputs!

  3. Impressive and engaging writeup! Investigating potential uses of AI in the legislation creation process seems very timely, I imagine there’s already hundreds of low-level staffers injecting delve-ridden texts into bills all over the US. Both the process and the democratic system itself will have to adjust to mitigate the risks. A direction in which this work could be extended is trying to see how real human beings interact with {malicious-,benign-}{AI,human} produced legislation.Sadly, I could access neither the deployed app nor the sources.

Cite this project

@misc{dutta2024multilingual,
  title = {{Multilingual Bias in Large Language Models: Assessing Political Skew Across Languages}},
  author = {Srishti Dutta and Akash Kundu},
  year = {2024},
  month = may,
  note = {Submitted to AI and Democracy Hackathon: Demonstrating the Risks, an Apart Research Sprint},
  howpublished = {\url{https://apartresearch.com/sprints/projects/multilingual-bias-in-large-language-models-assessing-political-skew-across-languages}},
  url = {https://apartresearch.com/sprints/projects/multilingual-bias-in-large-language-models-assessing-political-skew-across-languages}
}

Build something like this at the next Sprint

AI Collusion Research Sprint · Oct 23 - 25, 2026