Large language models are biased. Can logic help save them?

MIT researchers trained logic-aware language models to reduce harmful stereotypes like gender and racial biases. Close Turns out, even language models "think" they're biased. When prompted in ChatGPT, the response was as follows: "Yes, language models can have biases, because the training data reflects the biases present in society from which that data was collected. For example, gender and racial biases are prevalent in many real-world datasets, and if a language model is trained on that, it can perpetuate and amplify these biases in its predictions." A well-known but dangerous problem. Humans (typically) can dabble with both logical and stereotypical reasoning when learning. Still, language models mainly mimic the latter, an unfortunate narrative we've seen play out ad nauseam when the ability to employ reasoning and critical thinking is absent. So would injecting logic into the fray be enough to mitigate such behavior?  Scientists from MIT's Computer Science and Artificial Intelligence Laboratory (CSAIL) had an inkling that it might, so they set off to examine if logic-aware language models could significantly avoid more harmful stereotypes.