Sireesh Gururaja

I’m a PhD student at Carnegie Mellon University’s Language Technologies Institute, advised by Emma Strubell. I previously completed a masters degree here under the supervision of Carolyn Rose, and a BA in computer science at Columbia University. My work is supported by the Army Research Lab’s HTMDEC US Citizen Fellowship and the Mozilla Foundation.

My research focuses on NLP and AI tools that allows users in specialized domains to keep agency in their work. How can we empower people to customize and change their tools to reflect and be useful to how they see their own jobs, rather than how their boss or a tech company with a billion other users does? More concretely, I focus on user-customizable, on-device models that live in the browser, and how to effectively reason their limitations and update them. I’m also interested in the incentives that shape NLP research, whether funding, tooling, or culture.

Before coming to CMU, I spent six years in industry. I started at IBM Watson in 2015 on a team that did bespoke prototypes; I then moved to Kensho Technologies in 2018, where I spent three and a half years, first working as an ML engineer focused on NLP, then as the first lead of the ML Ops and Internal Tools team.

You can find my CV here.

news

Nov 03, 2026	I’m at UIST ‘26, presenting TractorBeam in the poster session (paper\|poster). I wrote about TractorBeam in a blog post, and you can find a full version of the study here.
Oct 07, 2026	I’m at 4S this week! This is my first time here, and I’ll be presenting an abstract about benchmarking that was chapter 3 of my thesis proposal. TractorBeam will also be at the Making and Doing session under the title Bifocal Reading: Bridging Close and Distant Reading with Collaborative Machine Annotation.
Apr 17, 2026	I was at the CHI-STAR workshop last week at CHI 2026, talking about collaborative annotation as an interface metaphor for AI. You can find the paper itself here, or take a look at the TractorBeam page to see how progress on a demo is going!

selected work

UIST EA ’26

TractorBeam: Personalized AI Sensemaking Support via Collaborative Machine Annotation

Sireesh Gururaja, Jordan Taylor, and Emma Strubell

In The 39th Annual ACM Symposium on User Interface Software and Technology, Detroit, MI, USA, Nov 2026

DOI
ACL ’25 Findings

Beyond Text: Expert Needs in Document Research

Sireesh Gururaja, Nupoor Gandhi, Jeremiah Milbauer, and 1 more author

Nov 2025

Abs PDF

Working with documents is a key part of almost any knowledge work, from contextualizing research in a literature review to reviewing legal precedent. Recently, as their capabilities have expanded, primarily text-based NLP systems have often been billed as able to assist or even automate this kind of work. But to what extent are these systems able to model these tasks as experts conceptualize and perform them now? In this study, we interview sixteen domain experts across two domains to understand their processes of document research, and compare it to the current state of NLP systems. We find that our participants processes are idiosyncratic, iterative, and rely extensively on the social context of a document in addition its content; existing approaches in NLP and adjacent fields that explicitly center the document as an object, rather than as merely a container for text, tend to better reflect our participants’ priorities, though they are often less accessible outside their research communities. We call on the NLP community to more carefully consider the role of the document in building useful tools that are accessible, personalizable, iterative, and socially aware.
Non-archival

Data-driven Design as a High-Impact, Ecologically Valid Benchmark for Document Understanding

Sireesh Gururaja, Junwon Seo, Hung-Yi Lin, and 3 more authors

Nov 2025

Abs PDF

In this work we present a challenge dataset for few- and zero-shot multimodal information extraction to support the data-driven design (DDD) of materials. The benchmark repurposes manually-verified tabular data from \citetjensen_machine_2019’s study of zeolite synthesis. The proposed dataset is intended to evaluate systems’ capabilities in information extraction, disambiguation, and normalization from tables and related text (e.g. captions), in both multimodal and text-only settings. We argue that data-driven design presents a promising task — data-rich, useful, and challenging — against which to benchmark next-generation information extraction systems.
EMNLP ’23

To Build Our Future, We Must Know Our Past: Contextualizing Paradigm Shifts in Natural Language Processing

Sireesh Gururaja, Amanda Bertsch, Clara Na, and 2 more authors

In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, Dec 2023

Abs DOI

NLP is in a period of disruptive change that is impacting our methodologies, funding sources, and public perception. In this work, we seek to understand how to shape our future by better understanding our past. We study factors that shape NLP as a field, including culture, incentives, and infrastructure by conducting long-form interviews with 26 NLP researchers of varying seniority, research area, institution, and social identity. Our interviewees identify cyclical patterns in the field, as well as new shifts without historical parallel, including changes in benchmark culture and software infrastructure. We complement this discussion with quantitative analysis of citation, authorship, and language use in the ACL Anthology over time. We conclude by discussing shared visions, concerns, and hopes for the future of NLP. We hope that this study of our field’s past and present can prompt informed discussion of our community’s implicit norms and more deliberate action to consciously shape the future.