Daben Liu

Principal Researcher, AI Foundation, CapitalOne

Joined

September 2024

Names

Daben Liu (Preferred)

Emails

****@capitalone.com (Confirmed)

****@gmail.com (Confirmed)

Personal Links

Career & Education History

Principal Researcher

AI Foundation, CapitalOne (capitalone.com)

2023 – Present

Advisors, Relations & Conflicts

Coauthor

Alfy Samuel

2023 – Present

Coauthor

Anoop Kumar

2023 – 2025

PhD Advisor

Douglas Preis

1996 – 1997

Expertise

ASR

1996 – Present

AI/ML

1996 – Present

Publications

Play by the Type Rules: Inferring Constraints for Small Language Models in Declarative Programs
Parker Glenn, Alfy Samuel, Daben Liu
- AITD@EurIPS 2025 Poster
- Readers: Everyone
Alignment-Weighted DPO: A principled reasoning approach to improve safety alignment
Mengxuan Hu, Vivek Datla, Anoop Kumar, Zihan Guan, Sheng Li, Alfy Samuel, Daben Liu
- ICLR 2026 Poster
- Readers: Everyone
Uncertainty as Feature Gaps: Epistemic Uncertainty Quantification of LLMs in Contextual Question-Answering
Yavuz Faruk Bakman, Sungmin Kang, Zhiqi Huang, Duygu Nur Yaldiz, Catarina G Belém, Chenyang Zhu, Anoop Kumar, Alfy Samuel, Daben Liu, Salman Avestimehr, Sai Praneeth Karimireddy
- ICLR 2026 Poster
- Readers: Everyone
Improving Consistency in Retrieval Augmented Systems with Group Similarity Reward
Faisal Hamman, Chenyang Zhu, Anoop Kumar, Xujun Peng, Sanghamitra Dutta, Daben Liu, Alfy Samuel
- Submitted to ICLR 2026
- Readers: Everyone
Play by the Type Rules: Inferring Constraints for LLM Functions in Declarative Programs
Parker Glenn, Alfy Samuel, Daben Liu
- ICLR 2026 Conference Withdrawn Submission
- Readers: Everyone
RAFFLES: Reasoning-based Attribution of Faults for LLM Systems
Chenyang Zhu, Spencer Hong, Jingyu Wu, Kushal Chawla, Yuhui Tang, Youbing Yin, Nathan Wolfe, Erin Babinsky, Daben Liu
- MTI-LLM @ NeurIPS 2025 Poster
- Readers: Everyone
Improving Consistency in Retrieval-Augmented Systems with Group Similarity Rewards
Faisal Hamman, Chenyang Zhu, Anoop Kumar, Xujun Peng, Sanghamitra Dutta, Daben Liu, Alfy Samuel
- NeurIPS 2025 - Reliable ML Workshop
- Readers: Everyone
Uncertainty as Feature Gaps: Epistemic Uncertainty Quantification of LLMs in Contextual Question-Answering
Yavuz Faruk Bakman, Zhiqi Huang, Chenyang Zhu, Anoop Kumar, Alfy Samuel, Daben Liu
- NeurIPS 2025 - Reliable ML Workshop
- Readers: Everyone
Refusal Tokens: A Simple Way to Calibrate Refusals in Large Language Models
Neel Jain, Aditya Shrivastava, Chenyang Zhu, Daben Liu, Alfy Samuel, Ashwinee Panda, Anoop Kumar, Micah Goldblum, Tom Goldstein
- COLM 2025
- Readers: Everyone
Refusal Tokens: A Simple Way to Calibrate Refusals in Large Language Models
Neel Jain, Aditya Shrivastava, Chenyang Zhu, Daben Liu, Alfy Samuel, Ashwinee Panda, Anoop Kumar, Micah Goldblum, Tom Goldstein
- SafeGenAi Poster
- Readers: Everyone

View all 11 publications

Co-Authors

View all 30 co-authors