Beyond excited to share that this is now out in @Nature! We show that despite efforts to remove overt racial bias, LLMs generate covertly racist decisions about people based on their dialect. Joint work with amazing co-authors @ria_kalluri, @jurafsky, and Sharese King. Valentin Hofmann (@vjhofmann) 💥 New paper 💥 We discover a form of covert racism in LLMs that is triggered by dialect features alone, with massive harms for affected groups. For example, GPT-4 is more likely to suggest that defendants be sentenced to death when they speak African American English. 🧵 — https://nitter.net/vjhofmann/status/1764687418626576445#m

→ View original post on X — @jurafsky, 2024-08-29 14:21 UTC