Tsvetshop NLP
@tsvetshop.bsky.social
Yulia Tsvetkov’s Group at the University of Washington @uwnlp.bsky.social
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!
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👉🏻🧵
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👉🏻🧵
July 22, 2025 at 3:17 PM
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!
Reposted by Tsvetshop NLP
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
We welcome any feedback and questions -- don't hesitate to reach out!
16/16
April 22, 2025 at 6:50 PM
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
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!
Excited to see where this takes the next generation of effective LLM assistants and agents!
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)
👉🏻🧵
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)
👉🏻🧵
February 24, 2025 at 10:26 PM
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!
Excited to see where this takes the next generation of effective LLM assistants and agents!
Reposted by Tsvetshop NLP
Thanks for this nice summary of our recent EMNLP paper! Work with @smfsamir.bsky.social and others at @tsvetshop.bsky.social
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:
Finding hidden biases in Wikipedia’s multilingual content
A new tool analyzes and addresses cultural disparities across language versions, paving the way for more balanced information.
www.cs.jhu.edu
January 17, 2025 at 6:14 PM
Thanks for this nice summary of our recent EMNLP paper! Work with @smfsamir.bsky.social and others at @tsvetshop.bsky.social