Recent Updates

Happening @ACL 2024 in Bangkok: I am organizing a Workshop on Human-Centered Large Langugae Modeling. Follow @HuCLLM

Happening Jun 2024 @NAACL in Mexico City: I Will be giving an oral presentation on our position paper Large Human Language Models: A Need and the Challenges

Happening Jun 2024 @NAACL 2024 in Mexico City: I will be a presenter at the Tutorial on From Text to Context: Contextualizing Language with Humans, Groups, and Communities for Socially Aware NLP

Apr 2024: Invited to attend the CRA Grad Cohort for Women Workshop in Minnesota, and my interview was recorded!

Apr 2024: Invited to the German Consulate New York to attend the symposium SMART MINDS MEET SMART MACHINES - AI FOR SCIENCE AND THE PUBLIC GOOD

Mar 2024: Giving a guest lecture to the NLP grad class on Transformer and Self-Attention

Mar 2024: Our position paper arguing for Large Human Language Models is accepted in NAACL 2024

Nikita Soni

Nikita Soni

I am a PhD candidate at Stony Brook University, New York, co-advised by H. Andrew Schwartz and Niranjan Balasubramanian . My research interest lies in Human-Centered Natural Language Processing and enabling Language Modeling with the context of the human behind the language.
Prior, I was working in the software industry exploring multiple facets of the software engineering world (details in CV). Personally, I'm a very outdoorsy person but also enjoy my own company.

Let's chat more over a cup of coffee.

PersonalNikita Soni
ProfessionalNikita Soni
Research Purpose

I am enthused about NLP's expanding outreach in our lives and its unexplored abilities to understand human nature better and more efficiently than ever. Language is more than words, it expresses identities, psychologies, cultures and much more. I find myself challenged in directing NLP language models to look beyond the current limitations and consider the human behind the language. The purpose of my research is to enable the growth of more empathy in an AI-future centric world, thereby augmenting humanity rather than detracting from it.

Recent Services

Reviewer for ARR (ACL) Feb 2024

Reviewer for ARR (NAACL) Dec 2023

PC member of ICWSM Data Challenge 2023

Reviewer for EMNLP 2023

Reviewer of Language Modeling & Analysis of Language Models Track, EMNLP 2022

PC member of The 5th workshop on Natural Language Processing and Computational Social Science (NLP+CSS), EMNLP 2022

Volunteer for Diversity & Inclusion Committee, NAACL Conference 2022

Research Publications

Archetypes and Entropy: Theory-Driven extraction of Evidence for Suicide Risk.

[pdf] CLPsych workshop in EACL 2024. workshop

Vasudha Varadarajan, Allison Lahnala, Adithya V Ganesan, Gourab Dey, Siddharth Mangalik, Ana-Maria Bucur, Nikita Soni, Rajath Rao, Kevin Lanning, Isabella Valejo, Lucie Flek, H Andrew Schwartz, Charles Welch, and Ryan L Boyd.

    Comparing Pre-trained Human Language Models: Is it Better with Human Context as Groups, Individual Traits, or Both? arXiv preprint

    [pdf] Nikita Soni, Niranjan Balasubramanian, H Andrew Schwartz, Dirk Hovy.

      Large Human Language Models: A Need and the Challenges. githubwebsite

      NAACL 2024. conference

      [pdf] Nikita Soni, João Sedoc, H Andrew Schwartz and Niranjan Balasubramanian.

        Robust language-based mental health assessments in time and space through social media

        IACT workshop at ACM SIGIR conference 2023. workshop

        [pdf] Siddharth Mangalik, Johannes C Eichstaedt, Salvatore Giorgi, Jihu Mun, Farhan Ahmed, Gilvir Gill, Adithya V Ganesan, Shashanka Subrahmanya, Nikita Soni, Sean AP Clouston, and H Andrew Schwartz.

          I slept like a baby: Using human traits to characterize deceptive ChatGPT and human text.

          IACT workshop at ACM SIGIR conference 2023. workshop

          [pdf] Nikita Soni, Salvatore Giorgi, David M. Markovitz, Vasudha Varadarajan, Siddharth Mangalik and H Andrew Schwartz.

            Human Language Modeling

            ACL-Findings (2022) conference

            [pdf] Nikita Soni, Matthew Matero, Niranjan Balasubramanian and H. Andrew Schwartz

              WWBP-SQT-lite: Dif erence Embeddings and Multi-level Models for Moments of Change Identification in Mental Health Forums

              NAACL Workshop on CLPsych (2022).workshop

              [pdf] Nikita Soni, Adithya V Ganesan, Vasudha Varadarajan, Juhi Mittal, Shashanka Subrahmanya, Matthew Matero, Sharath Chandra Guntuku, Johannes Eichstaedt, and H Andrew Schwartz.

                Detecting Dissonant Stance in Social Media: The Role of Topic Exposure.

                To appear in EMNLP Workshop on NLP+CSS (2022) workshop

                [pdf]Vasudha Varadarajan, Nikita Soni, Weixi Wang, Christian Luhmann, H Andrew Schwartz, and Naoya Inoue.

                  MeLT: Message-Level Transformer with Masked Document Representations as Pre-Training for Stance Detection

                  EMNLP-Findings (2021)conference

                  [pdf] Matthew Matero, Nikita Soni, Niranjan Balasubramanian and H. Andrew Schwartz

                    Experience

                    Education

                    Research Experience

                    Research Internships

                    Software Engineering Jobs

                    GET IN TOUCH