Michael Bendersky

Principal Researcher, Databricks, Databricks

Joined

July 2019

Names

Michael Bendersky

Emails

****@google.com (Confirmed)

****@gmail.com (Confirmed)

****@acm.org (Confirmed)

Personal Links

Career & Education History

Principal Researcher

Databricks, Databricks (databricks.com)

2025 – Present

Researcher

Google (google.com)

2012 – 2025

PhD student

University of Massachusetts, Amherst (umass.edu)

2007 – 2012

MS student

Technion, Technion (technion.ac.il)

2006 – 2007

Advisors, Relations & Conflicts

PhD Advisor

W. Bruce Croft

2007 – 2012

MSc Advisor

Oren Kurland

2006 – 2007

Expertise

Information Retrieval

Present

Agentic Search

Present

Reinforcement Learning for Tool Use

Present

Publications

Can QPP Choose the Right Query Variant? Evaluating Query Variant Selection for RAG Pipelines
Negar Arabzadeh, Andrew Drozdov, Michael Bendersky, Matei Zaharia
- SIGIR 2026
- Readers: Everyone
KARL: Knowledge Agents via Reinforcement Learning
Jonathan Daniel Chang, Andrew Drozdov, Shubham Toshniwal, Owen Oertell, Alexander R Trott, Jacob Portes, Abhay Gupta, Pallavi Koppol, Ashutosh Baheti, Sean Kulinski, Ivan Zhou, Irene Dea, Krista Opsahl-Ong, Simon Favreau-Lessard, Sean Owen, Jose Javier Gonzalez Ortiz, Arnav Singhvi, Xabi Andrade, Xinyi Wang, Kartik Sreenivasan et al. (6 additional authors not shown)
- OpenReview Archive Direct Upload
- Readers: Everyone
Predicting Task Performance with Context-aware Scaling Laws
Kyle Montgomery, David Park, Jianhong Tu, Michael Bendersky, Beliz Gunel, Dawn Song, Chenguang Wang
- CoRR 2025
- Readers: Everyone
Pathways of Thoughts: Multi-Directional Thinking for Long-form Personalized Question Answering
Alireza Salemi, Cheng Li, Mingyang Zhang, Qiaozhu Mei, Zhuowan Li, Spurthi Amba Hombaiah, Weize Kong, Tao Chen, Hamed Zamani, Michael Bendersky
- CoRR 2025
- Readers: Everyone
Predicting Task Performance with Context-aware Scaling Laws
Kyle Montgomery, David Park, Jianhong Tu, Michael Bendersky, Beliz Gunel, Dawn Song, Chenguang Wang
- KnowFM @ ACL 2025
- Readers: Everyone
MLAN: Language-Based Instruction Tuning Preserves and Transfers Knowledge in Multimodal Language Models
Jianhong Tu, Zhuohao Ni, Nicholas Crispino, Zihao Yu, Michael Bendersky, Beliz Gunel, Ruoxi Jia, Xin Liu, Lingjuan Lyu, Dawn Song, Chenguang Wang
- KnowFM @ ACL 2025
- Readers: Everyone
Refract ICL: Rethinking Example Selection in the Era of Million-Token Models
Arjun R. Akula, Kazuma Hashimoto, Krishna Srinivasan, Aditi Chaudhary, Karthik Raman, Michael Bendersky
- CoRR 2025
- Readers: Everyone
RMBoost: Reward Model Training With Preference-Conditional Multi-Aspect Synthetic Data Generation
Jiaming Shen, Ran Xu, Yennie Jun, Zhen Qin, Tianqi Liu, Carl Yang, Yi Liang, Simon Baumgartner, Michael Bendersky
- SSI-FM Poster
- Readers: Everyone
Inference Scaling for Long-Context Retrieval Augmented Generation
Zhenrui Yue, Honglei Zhuang, Aijun Bai, Kai Hui, Rolf Jagerman, Hansi Zeng, Zhen Qin, Dong Wang, Xuanhui Wang, Michael Bendersky
- ICLR 2025
- Readers: Everyone
Reasoning-Enhanced Self-Training for Long-Form Personalized Text Generation
Alireza Salemi, Cheng Li, Mingyang Zhang, Qiaozhu Mei, Weize Kong, Tao Chen, Zhuowan Li, Michael Bendersky, Hamed Zamani
- CoRR 2025
- Readers: Everyone

View all 205 publications

Co-Authors

View all 237 co-authors