Ruixin (Ray) Yang
   
杨瑞欣
I am an incoming MSCS student at Georgia Tech. I received my BSc degree in Computer Science and Statistics from University of British Columbia in the beautiful Vancouver, Canada.
My research interests lie in the field of Trustworthy and Social NLP, with the goal of building safe, reliable and socially-aware language models and applications. Specifically, I am interested in (1) Aligning large language models with diverse human preferences and social values; (2) Addressing the limitations of current LLMs that undermine their reliability, such as privacy leakage and uncertainty miscalibration; (3) Human-centered LLM evaluation.
During my undergrad years, I was a research assistant at Dartmouth College where I had the chance to work with Dr. Ruibo Liu and Prof. Soroush Vosoughi on Tool-augmented Language Models and LLM Alignment.
Email  / 
Github  / 
Google Scholar  / 
Linkedin  / 
Twitter  / 
Instagram
|
|
|
Confidence Calibration and Rationalization for LLMs via Multi-Agent Deliberation
Ruixin Yang,
Dheeraj Rajagopal,
Shirley Anugrah Hayati,
Bin Hu,
Dongyeop Kang
ICLR 2024 Workshop on Reliable and Responsible Foundation Models
OpenReview
/
arXiv
/
code
We propose Collaborative Calibration, a collaborative approach to elicit, calibrate, and rationalize prediction confidence of LLMs.
|
|
Training Socially Aligned Language Models on Simulated Social Interactions
Ruibo Liu,
Ruixin Yang,
Chenyan Jia,
Ge Zhang,
Diyi Yang,
Soroush Vosoughi
ICLR 2024
OpenReview
/
arXiv
/
code & data
Alignment training with data from multi-LLM simulated social interactions, as an efficient, effective, and stable alternative for RLHF.
|
|
Visual Analytics for Generative Transformer Models
*Raymond Li,
*Ruixin Yang,
Wen Xiao,
Ahmed AbuRa'ed,
Gabriel Murray,
Giuseppe Carenini
paper
/
arXiv
/
code & data
In this work, we present a novel visual analytical framework to support the analysis of transformer-based generative models.
|
|
Generalizing Morphological Inflection Systems to Unseen Lemmas
*Changbing Yang,
*Ruixin Yang,
Garrett Nicolai,
Miikka Silfverberg
SIGMORPHON 2022
paper
Competed for Shared Task 0: Generalization and Typologically Diverse Morphological Inflection and achieved the highest performance among all submission in both small and large training conditions.
|
I come from Nanjing, a beautiful and historical city that served as the capital of six ancient Chinese dynasties over the past two thousand years.
I like listening to Rock N' Roll, ranging from Progressive Rock to BritPop and Pop Rock. Some of my favourite bands/artists: Pink Floyd, Dire Straits, David Bowie, Yes, King Crimson, The Stone Roses, Oasis, Coldplay, Keane, 万能青年旅店, 罗大佑, 高旗/超载, 许巍.
I've also been known to (awkwardly) hoop, smash, and get 'Love'. (Style borrowed here from Prof. Schmidt)
|