May 6, 2024
Silent Curriculum
Aman Priyanshu, Supriti Vijay
Our project, "The Silent Curriculum," reveals how LLMs (Large Language Models) may inadvertently shape education and perpetuate cultural biases. Using GPT-3.5 and LLaMA2-70B, we generated children's stories and analyzed ethnic-occupational associations [self-annotated ethnicity extraction]. Results show strong similarities in biases across LLMs [cosine similarity: 0.87], suggesting an AI monoculture that could narrow young minds. This algorithmic homogenization [convergence of pre-training data, fine-tuning datasets, analogous guardrails] risks creating echo chambers, threatening diversity and democratic values. We urgently need diverse datasets and de-biasing techniques [mitigation strategies] to prevent LLMs from becoming unintended arbiters of truth, stifling the multiplicity of voices essential for a thriving democracy.
Bart Bussmann
Interesting experiment that shows how LLMs may have biases in generating childrens stories. I think for this hackathon, the experiments are bit far removed from a direct threat to democracy. It would also be interesting to see how you expect this to change in the feature and what can be done to mitigate the consequences of these biases.
Cite this work
@misc {
title={
@misc {
},
author={
Aman Priyanshu, Supriti Vijay
},
date={
5/6/24
},
organization={Apart Research},
note={Research submission to the research sprint hosted by Apart.},
howpublished={https://apartresearch.com}
}