Logo

Tomer Wolfson

Postdoctoral Fellow at the University of Pennsylvania School of Engineering and Applied Science.

GitHub
Google Scholar, Semantic Scholar
Publications
Teaching

About

I am a Postdoctoral Research Fellow at the University of Pennsylvania and a member of the Cognitive Computation Group led by Prof. Dan Roth.

My area of research lies at the intersection of Data Management and Natural Language Processing. I am interested in developing algorithms that are capable of understanding complex questions which involve reasoning over hundreds of documents in order to piece together an answer.

I was a PhD student at the Blavatnik School of Computer Science of Tel Aviv University, advised by Prof. Daniel Deutch and Prof. Jonathan Berant. During my PhD, in 2019-2024, I served as a research intern at the Allen Institute for AI. I received my BSc and MSc in computer science at Tel Aviv University.


Publications

Generating Tables from the Parametric Knowledge of Language Models.
Yevgeni Berkovitch, Oren Glickman, Amit Somech, Tomer Wolfson.
Preprint, under submission.


LINX: A Language Driven Generative System for Goal-Oriented Automated Data Exploration.
Tavor Lipman, Tova Milo, Amit Somech, Tomer Wolfson, Oz Zafar.
International Conference on Extending Database Technology (EDBT) 2025, in press.


Making Retrieval-Augmented Language Models Robust to Irrelevant Context.
Ori Yoran, Tomer Wolfson, Ori Ram, Jonathan Berant.
International Conference on Learning Representations (ICLR) 2024, in press.


Answering Questions by Meta-Reasoning over Multiple Chains of Thought.
Ori Yoran*, Tomer Wolfson*, Ben Bogin, Uri Katz, Daniel Deutch, Jonathan Berant.
Empirical Methods in Natural Language Processing (EMNLP) 2023, pages 5942–5966.


QAMPARI: An Open-domain Question Answering Benchmark for Questions with Many Answers from Multiple Paragraphs.
Samuel Joseph Amouyal, Tomer Wolfson, Ohad Rubin, Ori Yoran, Jonathan Herzig, Jonathan Berant. Third Workshop on Generation, Evaluation & Metrics (GEM), at EMNLP 2023, in press.


Weakly Supervised Text-to-SQL Parsing through Question Decomposition.
Tomer Wolfson, Daniel Deutch, Jonathan Berant.
Findings of the North American Chapter of the Association for Computational Linguistics (NAACL) 2022, pages 2528-2542.


Break, Perturb, Build: Automatic Perturbation of Reasoning Paths through Question Decomposition.
Mor Geva, Tomer Wolfson, Jonathan Berant.
Volume 10 of the Transactions of the Association for Computational Linguistics (TACL) 2022, pages 111-126.


Obtaining Faithful Interpretations from Compositional Neural Networks.
Sanjay Subramanian*, Ben Bogin*, Nitish Gupta*, Tomer Wolfson, Sameer Singh, Jonathan Berant, Matt Gardner.
Association for Computational Linguistics (ACL) 2020, pages 5594-5608.


Break It Down: A Question Understanding Benchmark.
Tomer Wolfson, Mor Geva, Ankit Gupta, Matt Gardner, Yoav Goldberg, Daniel Deutch, Jonathan Berant.
Volume 8 of the Transactions of the Association for Computational Linguistics (TACL) 2020, pages 183-198.


Explaining Queries over Web Tables to Non-Experts.
Jonathan Berant, Daniel Deutch, Amir Globerson, Tova Milo, Tomer Wolfson*.
IEEE 35th International Conference on Data Engineering (ICDE) 2019, pages 1570-1573.


Teaching

Tel Aviv University.
Lecturer (2021 - 2022).
Lecturer of the course “Web Data Management & Information Retrieval”. Developed slides and class projects on natural language processing, information retrieval, information extraction and ontology building.

Teaching Assistant (2018 - 2020).
Taught recitations of the “Web Data Management” course under Prof. Daniel Deutch. Developed slides and projects on natural language processing, information extraction and ontology building.