Kaiji Lu

Researcher, Pinterest Inc.

Joined

September 2020

Names

Kaiji Lu (Preferred)

Emails

****@andrew.cmu.edu (Confirmed)

****@gmail.com (Confirmed)

Personal Links

Homepage

DBLP

Semantic Scholar

Career & Education History

Researcher

Pinterest Inc. (pinterest.com)

2022 – Present

PhD student

Carnegie Mellon University (cmu.edu)

2017 – 2022

Advisors, Relations & Conflicts

No relations added

Expertise

Deep Learning

Present

Explanability

Present

NLP

Present

Publications

Grounding Neural Inference with Satisfiability Modulo Theories
Zifan Wang, Saranya Vijayakumar, Kaiji Lu, Vijay Ganesh, Somesh Jha, Matt Fredrikson
- NeurIPS 2023 spotlight
- Readers: Everyone
Learning Modulo Theories
Matt Fredrikson, Kaiji Lu, Saranya Vijayakumar, Somesh Jha, Vijay Ganesh, Zifan Wang
- 2023 (modified: 24 Apr 2023)
- CoRR 2023
- Readers: Everyone
Order-sensitive Shapley Values for Evaluating Conceptual Soundness of NLP Models
Kaiji Lu, Anupam Datta
- 2022 (modified: 24 Apr 2023)
- CoRR 2022
- Readers: Everyone
Influence Patterns for Explaining Information Flow in BERT
Kaiji Lu, Zifan Wang, Piotr Mardziel, Anupam Datta
- Published: 09 Nov 2021, Last Modified: 05 May 2023
- NeurIPS 2021 Poster
- Readers: Everyone
Machine Learning Explainability and Robustness: Connected at the Hip
Anupam Datta, Matt Fredrikson, Klas Leino, Kaiji Lu, Shayak Sen, Zifan Wang
- 2021 (modified: 03 Dec 2021)
- KDD 2021
- Readers: Everyone
Exploring Conceptual Soundness with TruLens
Anupam Datta, Matt Fredrikson, Klas Leino, Kaiji Lu, Shayak Sen, Ricardo Shih, Zifan Wang
- 2021 (modified: 24 Apr 2023)
- NeurIPS (Competition and Demos) 2021
- Readers: Everyone
Influence Patterns for Explaining Information Flow in BERT
Kaiji Lu, Zifan Wang, Piotr Mardziel, Anupam Datta
- 2021 (modified: 24 Apr 2023)
- NeurIPS 2021
- Readers: Everyone
ABSTRACTING INFLUENCE PATHS FOR EXPLAINING (CONTEXTUALIZATION OF) BERT MODELS
Kaiji Lu, Zifan Wang, Piotr Mardziel, Anupam Datta
- 28 Sept 2020 (modified: 05 May 2023)
- ICLR 2021 Conference Blind Submission
- Readers: Everyone
Abstracting Influence Paths for Explaining (Contextualization of) BERT Models
Kaiji Lu, Zifan Wang, Piotr Mardziel, Anupam Datta
- 2020 (modified: 30 Oct 2021)
- CoRR 2020
- Readers: Everyone
Gender Bias in Neural Natural Language Processing
Kaiji Lu, Piotr Mardziel, Fangjing Wu, Preetam Amancharla, Anupam Datta
- 2020 (modified: 30 Oct 2021)
- Logic, Language, and Security 2020
- Readers: Everyone

View all 13 publications

Kaiji Lu

Names

Emails

Personal Links

Career & Education History

Advisors, Relations & Conflicts

Expertise

Publications

Co-Authors