Research poster showing LLMs perform up to 20% worse on non-standard English dialects. Includes tables comparing performance across 6 dialects (African American, Appalachian, Chicano, Indian, Singaporean, Southern) and bar charts showing three grammar rules (existential it, zero copula, y'all) explain roughly half the accuracy decrease

🧵Excited to present our work at #EMNLP2025 “Analyzing Dialectal Biases in LLMs for Knowledge and Reasoning Benchmarks”!
Paper 📄 arxiv.org/abs/2510.00962
w/ Eileen Pan, Skyler Seto, @allisonkoe.bsky.social @maartjeterhoeve.bsky.social

New preprint! 👇

💜 We introduce PLUM, to teach LLMs to remember prior user conversations. An important step towards personalizing LLMs!

Details below!

Many thanks to Charlotte for being a great intern and driving this project, and to many members of MLR and Apple that helped get this work out 🙏