Lecturer & Principal Investigator
Department of Computer Science, Ariel University
Director, NLP for Human Sciences Lab
About
I am a Lecturer (Principal Investigator) in the Department of Computer Science, Ariel University, where I lead the NLP for Human Sciences Lab. My research explores the intersection of Artificial Intelligence and the Human Sciences, focusing on how Large Language Models (LLMs) can advance our understanding of complex human phenomena while enhancing scientific discovery itself.
Methodologically, I work on interpretable and causal NLP, with an emphasis on LLM interpretability, concept-based representations, and model-based reasoning that bridges data-driven AI and theory-driven science.
Before joining Ariel University, I was a post-doctoral researcher at Queen Mary University of London and Bar-Ilan University, working with Prof. Maria Liakata and Prof. Dana Atzil-Slonim on applying advanced NLP to psychotherapy research — aiming to uncover the mental processes and dynamics underlying effective therapeutic change.
I completed my B.Sc. (2015) in Psychology and Philosophy at Bar Ilan University, and my M.Sc. (2018) and Ph.D. (2024) in Computer Science in the Natural Language Processing Lab at Bar Ilan University under the supervision of Prof. Ido Dagan. My doctoral research focused on semantic representations, particularly the QASem project.
My broader academic interests span psychology, cognitive and social sciences, linguistics, philosophy, mathematics, and computational methods — fields that together shape a vision of AI as a catalyst for integrative scientific understanding. I am enthusiastic about cross-disciplinary collaborations of AI and Data-Science specialists with social sciences and humanities, aiming at revolutionizing the way we investigate, measure, and confirm or disprove scientific research questions in the "softer" sciences.
Industry Solutions & Consulting: Alongside my academic work, I design and deliver custom NLP architecture and custom-owned LLM solutions for research labs, startups, and private organizations.
Learn More →Research
The long-range goal of my work is to transform how empirical science is practiced in the human sciences — using the new ML/LLM toolbox not merely as a productivity aid, but as a fundamentally new instrument for measuring, modeling, and understanding human behavior, language, and cognition. I believe we are at an inflection point where AI can act as a catalyst for integrative, theory-grounded scientific discovery, enabling researchers to ask questions at a scale and resolution that were simply not feasible before.
Applying LLMs to therapy transcripts, social media timelines, and clinical texts to quantify behavior, mental states, and therapeutic processes at scale — with rigorous expert validation.
Investigating how LLMs encode conceptual meaning, cultural nuances, and cognitive structures — through mechanistic interpretability, latent space analysis, and concept-based representations.
Developing NLP workflows and evaluation frameworks that let researchers in social, behavioral, and health sciences rigorously apply AI to their empirical questions — bridging data-driven AI with theory-driven science.
The lab website is the primary, up-to-date window into our ongoing projects, team, and collaborations. This page offers a snapshot; visit there for the full picture.
Visit the Lab →PhD Work
In my Ph.D., we devised a natural way to break down the information conveyed by language using question-answer pairs. The QASem framework covers multiple layers of textual meaning; the tool takes a sentence and outputs QA pairs corresponding to its basic semantic units.
Demo · GitHub · Latest parser · pip install qasem_parser
Publications
"A Universal Vibe? Finding and Controlling Language-Agnostic Informal Register with SAEs" Under Review
arXiv preprint arXiv:2603.26236. 2026.
"Effective QA-driven Annotation of Predicate-Argument Relations Across Languages"
Proceedings of EACL 2026 (Long Papers), pp. 2484–2502, Rabat, Morocco. Association for Computational Linguistics. 2026.
JMIR Formative Research 2026; 10:e71230. doi:10.2196/71230. 2026.
"QA-Noun: Representing Nominal Semantics via Natural Language Question-Answer Pairs"
Proceedings of IJCNLP-AACL 2025, pp. 2727–2741, Mumbai, India. 2025.
Proceedings of CLPsych 2025, pp. 193–217, Albuquerque, New Mexico. Association for Computational Linguistics. 2025.
"QAPyramid: Fine-grained Evaluation of Content Selection for Text Summarization"
Proceedings of COLM 2025. Association for Computational Linguistics. 2025.
"Large language models for mental health"
arXiv preprint arXiv:2411.11880. 2024.
"Explicating the Implicit: Argument Detection Beyond Sentence Boundaries"
Proceedings of ACL 2024 (Volume 1: Long Papers), pp. 16394–16409, Bangkok, Thailand. 2024.
"QA-Adj: Adding Adjectives to QA-based Semantics"
Proceedings of the 4th International Workshop on Designing Meaning Representations, pp. 74–88, Nancy, France. ACL. 2023.
"QASem Parsing: Text-to-text Modeling of QA-based Semantics"
Proceedings of EMNLP 2022, pp. 7742–7756, Abu Dhabi. Association for Computational Linguistics. 2022.
"Opinion-based Relational Pivoting for Cross-domain Aspect Term Extraction"
Proceedings of WASSA 2022, pp. 104–112. Association for Computational Linguistics. 2022.
"QA-Align: Representing Cross-Text Content Overlap by Aligning Question-Answer Propositions"
Proceedings of EMNLP 2021, pp. 9879–9894. Association for Computational Linguistics. 2021.
"QANom: Question-answer driven SRL for nominalizations"
Proceedings of COLING 2020, pp. 3069–3083. 2020.
"QADiscourse — Discourse Relations as QA Pairs: Representation, Crowdsourcing and Baselines"
Proceedings of EMNLP 2020, pp. 2804–2819. Association for Computational Linguistics. 2020.
"Controlled Crowdsourcing for High-Quality QA-SRL Annotation"
Proceedings of ACL 2020, pp. 7008–7013. Association for Computational Linguistics. 2020.
Teaching
Object Oriented Programming — Lecturer, Department of Computer Science, Ariel University (2026)
Databases — Lecturer, Department of Computer Science, Ariel University (2025–present)
Advanced Models of Language Understanding — Lecturer, Department of Computer Science, Ariel University (2025–present)
Artificial Neural Networks (27-436) — Lecturer, Neuroscience Department, Bar Ilan University (2023–2024)
Object Oriented Programming (89-111) — Teaching Assistant, Department of Computer Science, Bar Ilan University (2019–2020)
Discrete Mathematics 1 (89-195) — Teaching Assistant, Department of Computer Science, Bar Ilan University (2019)
Text Understanding (89-565) — Teaching Assistant, Department of Computer Science, Bar Ilan University (2018)
Contact
For consulting enquiries, please visit the Applied NLP Architecture & Consulting page for details on project scope and availability.