Bingbing Wen

I am a PhD student at University of Washington. I'm fortunate to be advised by Prof. Bill Howe and Prof. Lucy Lu Wang.

My research focuses on building trustworthy foundation models at the intersection of NLP and AI. I work on three areas: data curation and synthesis for high-quality pretraining/posttraining, model training with techniques such as mixture-of-LoRA experts and reinforcement learning, and evaluation through instruction-following benchmarks, context-perturbation methods for abstention, and analyses of spurious correlations.

Email  |  Google Scholar  |  LinkedIn  |  Twitter  | 

profile photo
News
Selected Publications
sym

MARVEL: Modular Abstention for Reliable and Versatile Expert LLMs
Bingbing Wen, Faeze Brahman, Zhan Su , Shangbin Feng, Yulia Tsvetkov, Lucy Lu Wang, Bill Howe
ICML Reliable Foundation Model Workshop & NeurIPS Submission

sym

Do Language Models Mirror Human Confidence? Exploring Psychological Insights to Address Overconfidence in LLMs
Chenjun Xu*, Bingbing Wen*, Bin Han, Robert Wolfe, Lucy Lu Wang, Bill Howe
ACL2025 findings

sym

Know Your Limits: A Survey of Abstention in Large Language Models
Bingbing Wen, Jihan Yao, Shangbin Feng, Chenjun Xu, Yulia Tsvetkov, Bill Howe, Lucy Lu Wang
TACL2025, ACL2025 Oral

sym

AutoScale-Automatic Prediction of Compute-optimal Data Composition for Training LLMs
Feiyang Kang*, Yifan Sun*, Bingbing Wen, Si Chen, Dawn Song, Rafid Mahmood, Ruoxi Jia
COLM2025

sym

Characterizing LLM Abstention Behavior in Science QA with Context Perturbations
Bingbing Wen, Bill Howe, Lucy Lu Wang
EMNLP2024 Findings

sym

InfoVisDial: An Informative Visual Dialogue Dataset by Bridging Large Multimodal and Language Models
Bingbing Wen, Zhengyuan Yang, Jianfeng Wang, Zhe Gan, Bill Howe, Lijuan Wang

Internship at Microsoft Azure AI

sym

CCQ: cross-class query network for partially labeled organ segmentation

Xuyang Liu*, Bingbing Wen*,Sibei Yang
AAAI, 2023

sym

ExpScore: Learning metrics for recommendation explanation

Bingbing Wen,Yunhe Feng, Yongfeng Zhang, Chirag Shah
WWW, 2022

Reviewing
  • NeurIPS: 2023/2024
  • NeurIPS dataset and benchmark: 2023/2024
  • ICLR: 2023/2024
  • EMNLP: 2022/2023
  • AAAI: 2024
  • WACV: 2024/2025

A special thanks to Yujie Li .