Check out the full paper here:
🔗 lnkd.in/dtsH3gaX
🤗 lnkd.in/d7diuBJh

#ACL2025 #ACL #NLProc #NLP #AI #DigitalDivide #LLM #AIethics #sociotechnical

We argue for designing NLP systems that actively account for socioeconomic linguistic variation.
Bridging the AI gap means more than just making tools accessible—it means making them equitable.

These aren't just linguistic quirks—they point to real risks of AI reinforcing the digital divide.
Even as LLMs become widespread, they're not being used—or served—equally.

📊 Higher-SES users:
– Use more abstract & concise prompts
– Focus on topics like "inclusivity" & "travel"
– Use AI for work and study related queries
📎 Lower-SES users:
– Use more concrete language
– Personify the AI more (e.g., “hello”, “thank you”)
– Ask more practical, day-to-day questions

We surveyed 1,000 people from diverse SES backgrounds and analyzed 6,482 prompts from their real previous interactions with LLMs.
What we found: SES significantly shapes how people use and experience generative AI.