I’m an Assistant Professor at MIT EECS and a member of CSAIL. I study Natural Language Processing (NLP) and AI systems.

My research seeks to answer questions like: How do we program intelligent systems that are partly specified in natural language, that process natural language at scale, and whose quality and cost can be optimized using language models? And how do we develop more effective and sample-efficient learning algorithms by leveraging the priors that language models encode?

To answer these questions, I develop new models, algorithms, abstractions, and benchmarks for declarative AI programming, for composing and scaling retrieval and reasoning, and for learning from sparse and verbalized feedback.

My work is often consolidated into open-source research systems, like ColBERT, which introduced the late interaction paradigm that has helped shape the modern landscape of search, DSPy, the first and most widely used declarative programming model for LLM systems, GEPA, a genetic learning algorithm, and RLMs, an inference-time scaling paradigm. These have all grown into large open-source communities and three of them are now downloaded several millions of times every month.

I received my Ph.D. at Stanford, where I was advised by Matei Zaharia and Christopher Potts, was part of Stanford NLP, and was supported by the Apple Scholars in AI/ML fellowship. Before starting at MIT, I worked as a Research Scientist at Databricks.

Teaching

6.8610 Advanced NLP, w/ Jacob Andreas & Chris Tanner. Spring 2026.
6.7960 Deep Learning, w/ Sara Beery & Kaiming He. Fall 2025.

PhD Students and Postdocs

Alex L. Zhang (with Tim Kraska)
Diane Tchuindjo (with Devavrat Shah)
Jacob X. Li
Matthew Yang (incoming PhD student)
Noah Ziems (visiting MIT; with Meng Jiang at ND)
Rikiya Takehi (incoming PhD student)
Souradip Chakraborty (incoming postdoc)

MEng and UROP students.

Nathaniel Morgan (UROP)
Ziyad Hassan (MEng)

Former MS/PhD Mentees prior to MIT: Dilara Soylu (Stanford), Jan Luca Scheerer (ETH Zurich), Krista Opsahl-Ong (Stanford), Lakshya A Agrawal (UC Berkeley), Michael Ryan (Stanford), and others.

Recent & Selected Research

For a complete list of publications, see Google Scholar.

Pedagogical RL: Teaching Models to Teach Themselves from Privileged Information
S Chakraborty, N Ziems, F Huang, M Jiang, A S Bedi, O Khattab
Blog 2026 | blog

OBLIQ-Bench: Exposing Overlooked Bottlenecks in Modern Retrievers with Latent and Implicit Queries
D Tchuindjo, D Shah, O Khattab
Preprint 2026 | paper

Meta-Harness: End-to-End Optimization of Model Harnesses
Y Lee, R Nair, Q Zhang, K Lee, O Khattab, C Finn
Preprint 2026 | paper

Recursive Language Models
A Zhang, T Kraska, O Khattab
Preprint 2025 | paper

GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
LA Agrawal, S Tan, D Soylu, N Ziems, …, D Klein, M Zaharia, O Khattab
ICLR 2026 (Oral) | paper

Reasoning-Intensive Regression
D Tchuindjo, O Khattab
ACM CAIS 2026 | paper

Composing Policy Gradients and Prompt Optimization for Language Model Programs
N Ziems, D Soylu, L A Agrawal, I Miller, L Lai, …, C Potts, O Khattab
ACM CAIS 2026 | paper

WARP: An Efficient Engine for Multi-Vector Retrieval
JL Scheerer, M Zaharia, C Potts, G Alonso, O Khattab
SIGIR 2025 (Best Paper Award) | paper

FreshStack: Building Realistic Benchmarks for Evaluating Retrieval on Technical Documents
N Thakur, J Lin, S Havens, M Carbin, O Khattab, A Drozdov
NeurIPS 2025 | paper

LangProBe: a Language Programs Benchmark
S Tan, LA Agrawal, A Singhvi, L Lai, …, O Khattab, K Sen, M Zaharia
EMNLP 2025 Findings | paper

Drowning in Documents: Consequences of Scaling Reranker Inference
M Jacob, E Lindgren, M Zaharia, M Carbin, O Khattab, A Drozdov
ReNeuIR 2025 | paper

PAPILLON: PrivAcy Preservation from Internet-based and Local Language MOdel ENsembles
L Siyan, VC Raghuram, O Khattab, J Hirschberg, Z Yu
NAACL 2025 | paper

Fine-Tuning and Prompt Optimization: Two Great Steps that Work Better Together
D Soylu, C Potts, O Khattab
EMNLP 2024 | paper

Optimizing Instructions and Demonstrations for Multi-Stage Language Model Programs
K Opsahl-Ong, M Ryan, J Purtell, D Broman, C Potts, M Zaharia, O Khattab
EMNLP 2024 | paper

Assisting in Writing Wikipedia-like Articles From Scratch with Large Language Models
Y Shao, Y Jiang, T Kanell, P Xu, O Khattab, M Lam
NAACL 2024 | paper

DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines
O Khattab, A Singhvi, P Maheshwari, Z Zhang, K Santhanam, …, H Miller, M Zaharia, C Potts
ICLR 2024 (Spotlight) | paper

Holistic evaluation of language models
P Liang, R Bommasani, T Lee, D Tsipras, D Soylu, …, O Khattab, …, Y Zhang, Y Koreeda
TMLR 2023 | paper
Note: This is a multi-component, 50-author project. O Khattab directed the Information Retrieval evaluation.

Demonstrate-Search-Predict: Composing retrieval and language models for knowledge-intensive NLP
O. Khattab, K. Santhanam, X. Li, P. Liang, C. Potts, M. Zaharia
ArXiv 2022 | paper | code

PLAID: An Efficient Engine for Late Interaction Retrieval
K. Santhanam*, O. Khattab*, C. Potts, M. Zaharia
CIKM 2022 | paper | (* denotes co-first authors)

ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interaction
K. Santhanam*, O. Khattab*, J. Saad-Falcon, C. Potts, M. Zaharia
NAACL 2022 | paper | (* denotes co-first authors)

Hindsight: Posterior-guided Training of Retrievers for Improved Open-Ended Generation
A. Paranjape, O. Khattab, C. Potts, M. Zaharia, Christopher D. Manning
ICLR 2022 | paper

Baleen: Robust Multi-Hop Reasoning at Scale via Condensed Retrieval
O. Khattab, C. Potts, M. Zaharia
NeurIPS 2021 (Spotlight) | paper

On the Opportunities and Risks of Foundation Models
Stanford’s Center for Research on Foundation Models (CRFM), with 113 co-authors
Contributions to: Systems, Modeling, and Reasoning & Search
ArXiv 2021 | paper

Relevance-guided Supervision for OpenQA with ColBERT
O. Khattab, C. Potts, M. Zaharia
TACL 2021 | paper

ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT
O. Khattab and M. Zaharia
SIGIR 2020 | paper | code

Blog Posts

Recursive Language Models
A. Zhang, O. Khattab | post

On Impactful AI Research
O. Khattab | post

The Shift from Models to Compound AI Systems
M. Zaharia, O. Khattab, L. Chen, J. Q. Davis, H. Miller, C. Potts, J. Zou, M. Carbin, J. Frankle, N. Rao, A. Ghodsi
Berkeley Artificial Intelligence Research | post

A Guide to Large Language Model Abstractions
P. Y. Zhong, H. He, O. Khattab, C. Potts, M. Zaharia , H, Miller
Two Sigma Articles | post

Building Scalable, Explainable, and Adaptive NLP Models with Retrieval
O. Khattab, C. Potts, M. Zaharia
Stanford AI Lab (SAIL) blog | post

A moderate proposal for radically better AI-powered Web search. Stanford HAI blog.
O. Khattab, C. Potts, M. Zaharia
Stanford HAI blog | post

Last Update: May 2026