Novel cognitive science grounded approach to preference modeling: synthetic counterfactual training + attention-based attribute integration. Impressive empirical validation across 45 communities with human evaluation confirming interpretability claims. This opens exciting research directions!

Stella Li@stellali.bsky.social · last yr.

WHY do you prefer something over another? Reward models treat preference as a black-box😶‍🌫️but human brains🧠decompose decisions into hidden attributes We built the first system to mirror how people really make decisions in our recent COLM paper🎨PrefPalette✨ Why it matters👉🏻🧵

I had always wanted to work on something that can combine my love for fiction and NLP research, making this project a lot of fun. Huge thanks to the wonderful @melaniesclar.bsky.social and @tsvetshop.bsky.social! We welcome any feedback and questions -- don't hesitate to reach out! 16/16

Effective decision-making starts with asking the right questions. Our new framework, ALFA, teaches LLMs to ask questions through fine-grained attributes in expert domains. Excited to see where this takes the next generation of effective LLM assistants and agents!

Stella Li@stellali.bsky.social · 2y ago

Asking the right questions can make or break decisions in fields like medicine, law, and beyond✴️ Our new framework ALFA—ALignment with Fine-grained Attributes—teaches LLMs to PROACTIVE seek information through better questions through **structured rewards**🏥❓ (co-led with @jiminmun.bsky.social) 👉🏻🧵

Thanks for this nice summary of our recent EMNLP paper! Work with @smfsamir.bsky.social and others at @tsvetshop.bsky.social

JHU Computer Science@jhucompsci.bsky.social · 2y ago

A new tool analyzes and addresses cultural disparities across language versions in @wikipedia.bsky.social’s content, paving the way for more balanced information. Learn more: