Sathvik Nair

I'm a PhD candidate in Linguistics at the University of Maryland, focusing on computational psycholinguistics. I am advised by Profs. Philip Resnik and Colin Phillips. My research is supported by the NSF GRFP.

Originally from the Bay Area, I graduated from UC Berkeley with bachelor's degrees in Cognitive Science and Computer Science. There, I closely collaborated with Dr. Stephan Meylan on projects in Profs. Mahesh Srinivasan and Tom Griffiths' groups. Afterwards, I worked as a software engineer at Amazon Web Services in Boston and decided to stay on the East Coast for grad school. I generally accept he/him pronouns.

News & Highlights

December 2025: Our paper on predictive coding (co-led with Chiebuka Ohams) is out in the Journal of Memory and Language!

Fall 2025: Designed & taught my own course - an undergraduate seminar on prediction and computational psycholinguistics!

June 2025: Defended my qualifying paper on modeling speeded cloze response latencies. Officially a PhD candidate!

March 2025: Presented a talk on argument roles and a poster on modeling semantic information at HSP, here at UMD!

November 2024: Attended EMNLP, where I presented on semantic roles with Rosa Lee at the main conference and on syntactic generalization at CoNLL.

June 2024: Gave my first conference talk on tokenization at SciL at UC Irvine!

April 2024: Awarded the NSF GRFP!

February 2024: Gave a Language Science Lunch Talk on my background and research goals at the Maryland Language Science Center!

January 2024: Facilitated an interactive workshop on LLMs at the Maryland Language Science Center's Winter Storm series.

December 2023: Presented my first paper of grad school on tokenization and modeling reading times at EMNLP in Singapore!

March 2023: Presented on the relationship between words and context at HSP 2023 in Pittsburgh!

April 2022: Awarded a NSF GRFP Honorable Mention!

December 2021: Paper published in Cognition!

December 2020: Presented a paper based on my thesis at the CogALex workshop at COLING 2020!

May 2020: Awarded Highest Honors and the Glushko Prize for Outstanding Undergraduate Research in Cognitive Sciences for my thesis on polysemy!

Research

Prediction is a key principle of human language processing. It has also been key to developing language models that produce fluent text and effectively estimate next-token probabilities. My research involves developing and evaluating models of prediction in humans, based on what we know about machines. I'm focusing on three major directions: estimating probability above (and below) the level of individual "words," comparing human and model-based estimates of predictability, and modeling the cognitive mechanisms behind predictive processing.

Publications

Chiebuka Ohams*, Sathvik Nair*, Shohini Bhattasali, & Philip Resnik. A predictive coding model for online sentence processing. (* denotes equal contribution) Journal of Memory and Language, 2026 [link] [preprint]

Katherine Howitt, Sathvik Nair, Allison Dods, & Robert Hopkins. Generalizations across filler-gap dependencies in neural language models. CoNLL 2024 [link] [pdf]

Eun-Kyoung Rosa Lee, Sathvik Nair & Naomi Feldman. A Psycholinguistic Evaluation of Language Models' Sensitivity to Argument Roles. EMNLP Findings 2024 [link] [pdf]

Sathvik Nair & Philip Resnik. Words, Subwords, and Morphemes: What Really Matters in the Surprisal-Reading Time Relationship? EMNLP Findings 2023 [link] [pdf]

Stephan Meylan, Sathvik Nair, & Tom Griffiths. Evaluating Models of Robust Word Recognition with Serial Reproduction. Cognition, 2021 [link] [pdf]

Sathvik Nair, Mahesh Srinivasan, & Stephan Meylan. Contextualized Word Embeddings Encode Aspects of Human-Like Word Sense Knowledge. CogALex @ COLING 2020 [link] [pdf]

Peer-Reviewed Conference Presentations

Eun-Kyoung Rosa Lee, Sathvik Nair & Naomi Feldman. (Un)likely words in context: A divergence between humans and large language models. [abstract] [talk recording]

Sathvik Nair., Cassandra Jacobs, Philip Resnik & Colin Phillips. Words, Subwords, and Morphemes: Surprisal Theory and Units of Prediction. Poster at HSP 2025 [abstract]

Sathvik Nair, Katherine Howitt, Allison Dods & Robert Hopkins. LMs are not good proxies for human language learners. Talk at BUCLD 2024

Sathvik Nair & Philip Resnik. Words, Subwords, and Morphemes: What Really Matters in the Surprisal-Reading Time Relationship? Talk at SciL 2024, [abstract]

Sathvik Nair., Colin Phillips, & Philip Resnik. Words, Subwords, and Morphemes: Surprisal Theory and Units of Prediction. Poster at HSP 2024 [abstract]

Katherine Howitt, Sathvik Nair, Allison Dods & Robert Hopkins (2024) Acquiring generalizations across unbounded dependencies: How language models can provide insight into first language acquisition. Poster at MASC-SLL 2024

Sathvik Nair, Konstantine Kahadze & Philip Resnik. The Impacts of Subword Tokenization on Psycholinguistic Modeling. Poster at MASC-SLL 2024

Sathvik Nair, Shohini Bhattasali, Philip Resnik & Colin Phillips. How far does probability take us when measuring psycholinguistic fit? Evidence from Substitution Illusions and Speeded Cloze Data. Poster at HSP 2023 [abstract]

Collaborators, Mentors, Friends, and other Co-Conspirators

Research is never done in a vacuum, and publications don't reflect everyone who's intellectually influenced me. Here are some of those people. Many are connected with UMD's CLIP Lab and Language Science Center, which bring together researchers approaching computation and language (more broadly) from all sorts of perspectives.

UMD Cohort: Sebastián Mancha, Utku Türk, Sarah Boukendour, Cassandra Caragine, Lydia Quevedo, Allison Dods, Malhaar Shah, Sathvik Nair (SUS CLAMS for short)
Labmates: Rosa Lee, Katherine Howitt, Alba Jorquera Jiménez de Aberásturi, Novak Xingyu Shi, Rupak Sarkar, Alexander Hoyle, Dr. Pranav Goel, London Dixon, Dr. Masato Nakamura, Carmen Tang, Joselyn Rodriguez, Neha Srikanth, Nishant Balepur, Zongxia Li, Ishani Mondal
Undergraduate and Master's Collaborators (* = direct mentorship): Konstantine Kahadze*, Robert Hopkins*, Chiebuka Ohams, Ziying Zhang
Teachers and Mentors: Prof. Naomi Feldman, Prof. Shohini Bhattasali, Prof. Ellen Lau, Prof. Alexander Williams, Prof. Yi Ting Huang, Prof. Bob Slevc, Dr. Shevaun Lewis, Prof. Rachel Rudinger, Prof. Hal Daumé III, Prof. Caroline Charpentier, Prof. Cassandra Jacobs, Dr. Samer Nour Eddine, Dr. Byung-Doh Oh

Teaching

At UMD:

LING449B-Undergraduate Seminar in Psycholinguistics: Prediction, Computation & Language Processing: Instructor of record in Fall 2025
ARHU299-Machine Learning in Language and Art: Teaching Assistant in Fall 2024, primary instructor Prof. Omar Agha
LING200-Introduction to Linguistics: Teaching Assistant in Fall 2023, primary instructor Dr. Peggy Antonisse

At UC Berkeley:

COGSCI 131-Computational Models of Cognition: Undergraduate student instructor in Spring 2020
DATA 8-Foundations of Data Science: Undergraduate student instructor from Spring-Fall 2019, tutor from Spring-Fall 2018.

Miscellaneous

Other projects (not just academic) and information.

If you're applying to grad school in (computational) cognitive/language sciences and/or the GRFP, please reach out! I'm also happy to share my materials upon request.
I've helped out with a couple software tools for open and reproducible science:
- minicons, library to extract metrics from language models: contributor, led by Prof. Kanishka Misra.
- childes-db, a flexible and reproducible interface to multilingual child language corpora: co-maintainer with Jess Mankewitz, Prof. Mike Frank and others, led by Dr. Stephan Meylan and Dr. Mika Braginsky.
Large Language Models & Levels of Analysis: What 40-year-old Neuroscience Research can Tell Us About Modern AI – Applying fundamental ideas from cognitive science (Marr's levels of analysis) to explain various kinds of language models and argue how we can't say LLMs "understand" language like humans do.
GPT-3: An AI Breakthrough, but not Coming for Your Job – Article describing GPT-3, reactions from the press and experts, and research-backed opinions on the technology's limitations for Skynet Today (AI news publication). Coauthored with Daniel Bashir
How Biases in Language get Perpetuated by Technology – Towards Data Science article on personal project investigating gender, racial, and religious bias through analogy evaluation with static word embeddings (GloVe)
Workshop on NLP/ML– given at the Spectra 3.0 hackathon. Presented overview of the field and sentiment classification demo on tweets related to mental health.
Letters for Black Lives- I was involved with writing & curating resources for the South Asian community on anti-Blackness, including Hindi translation.
Here are some organizations whose work I care about: DMV Mutual Aid, Kalama Mutual Aid, Queer in AI, Bay Area Solidarity Summer
Outside of work, I enjoy (listening to, practicing, performing, composing, curating showcases with) music of all kinds, making and sharing home-cooked meals, and exploring historical and natural spots in the DC area and the East Coast via foot and public transit.

Website Template