Helia Hashemi

About

I am a Senior Researcher in the Efficient AI team. I am based in Microsoft Research New England in Cambridge, Massachusetts. My work explores retrieval and optimization techniques as well as model architectures to enhance the efficiency of large language models.

Prior to joining Microsoft in 2024, I completed my Ph.D. in Computer Science at the University of Massachusetts Amherst (opens in new tab) where I worked under supervision of W. Bruce Croft (opens in new tab) at the Center for Intelligent Information Retrieval (opens in new tab). My Ph.D. Dissertation studies Retrieval-Augmented Representation Learning for Information Retrieval. During the course of my Ph.D., I was named a Bloomberg Data Science Ph.D. Fellow (opens in new tab), won a Best Short Paper Honorable Mention Award from ICTIR 2019, and completed multiple Research Internships at Google, Microsoft, and Spotify.

I regularly publish at major information retrieval and natural language processing venues, such as SIGIR, WWW, CIKM, and ACL.

Publications:

Cost-Aware Retrieval-Augmentation Reasoning Models with Adaptive Retrieval Depth
H. Hashemi, V. Rühle, S. Rajmohan
WWW 2026

Retrieval Augmented Representation Learning for Information Retrieval
H. Hashemi
Ph.D. Dissertation

LLM-Rubric: A Multidimensional, Calibrated Approach to Automated Evaluation of Natural Language Texts
H. Hashemi, J. Eisner, C. Rosset, B. Van Durme, C. Kedzie
ACL 2024

Dense Retrieval Adaptation using Target Domain Description
H. Hashemi, Y. Zhuang, S. Kothur, S. Prasad, E. Meij, W. B. Croft
ICTIR 2023

Stochastic Optimization of Text Set Generation for Learning Multiple Query Intent Representations
H. Hashemi, H. Zamani, W. B. Croft
CIKM 2022

Learning Multiple Intent Representations for Search Queries
H. Hashemi, H. Zamani, W. B. Croft
CIKM 2021

Neural Instant Search for Music and Podcast
H. Hashemi, A. Pappu, M. Tian, P. Chandar, M. Lalmas, B. Carterette
KDD 2021

Passage Similarity and Diversification in Non-factoid Question Answering
L. Vikraman, A. Montazeralghaem, H. Hashemi, W. B. Croft, J. Allan
ICTIR 2021

Current Challenges and Future Directions in Podcast Information Access
R. Jones, H. Zamani, M. Schedl, C. Chen, S. Reddy, A. Clifton, J. Karlgren, H. Hashemi, A. Pappu, Z. Nazari, L. Yang, O. Semerci, H. Bouchard, B. Carterette
SIGIR 2021

Guided Transformer: Leveraging Multiple External Sources for Representation Learning in Conversational Search
H. Hashemi, H. Zamani, W. B. Croft
SIGIR 2020

ANTIQUE: A Non-factoid Question Answering Benchmark
H. Hashemi, M. Aliannejadi, H. Zamani, W. B. Croft
ECIR 2019

Performance Prediction for Non-factoid Question Answering
H. Hashemi, H. Zamani, W. B. Croft
ICTIR 2019