[grobbyy]

A basic problem is they're trained on the Internet, and take on all the biases. Ask any of them so purposed edX to MIT or wrote the platform. You'll get back official PR. Look at a primary source (e.g. public git history or private email records) and you'll get a factual story.

The tendency to reaffirm popular beliefs would make current LLMs almost useless for actual historical work, which often involves sifting fact from fiction.

[dmix]

Couldn’t LLMs cite primary sources much the same way as a textbook or Wikipedia? Which is how you circumvent the biases in textbooks and wikipedia summaries?

[bandrami]

They can, but they also hallucinate non-existent references:

https://journals.sagepub.com/doi/10.1177/05694345231218454

[simonw]

A raw LLM is a bad tool for citations, because you can't guarantee that their model weights will contain accurate enough information to be citable.

Instead, you should find the primary sources through other means and then paste them into the LLMs to help translate/evaluate/etc, which is what this author is doing.

[Almondsetat]

Circumventing the bias would mean providing a uniform sampling of the primary sources, which is not guaranteed to happen