Uri Katz

PhD Candidate in Computer Science

Bar-Ilan University · Advised by Yoav Goldberg

My research focuses on natural language processing — specifically on how we can build systems that understand and retrieve information from text in more flexible, human-like ways. I’m interested in named entity recognition beyond fixed categories, question answering that requires complex reasoning, and tools that help researchers explore scientific literature more effectively.

News

Feb 2026 New preprint on understanding usage and engagement in AI-powered scientific research tools.
Oct 2025 Paper on NER Retriever accepted at Findings of EMNLP 2025.
Sep 2024 Knowledge Navigator accepted at Findings of EMNLP 2024.
Oct 2023 NERetrieve accepted at Findings of EMNLP 2023.
Oct 2023 Meta-reasoning over chains of thought accepted at EMNLP 2023.

Selected Research

Knowledge Navigator: LLM-guided Browsing Framework for Exploratory Search in Scientific Literature
Findings of EMNLP 2024

Knowledge Navigator: LLM-guided Browsing Framework for Exploratory Search in Scientific Literature

Uri Katz, Mosh Levy, Yoav Goldberg

Researchers often struggle to explore unfamiliar scientific topics — keyword search only works when you already know what to look for. Knowledge Navigator uses an LLM to iteratively browse a paper's citation graph, reading abstracts and deciding which references to follow, much like a curious researcher would. It generates structured, multi-faceted summaries of a research area from a single seed paper.

NERetrieve: Dataset for Next Generation Named Entity Recognition and Retrieval
Findings of EMNLP 2023

NERetrieve: Dataset for Next Generation Named Entity Recognition and Retrieval

Uri Katz*, Matan Vetzler*, Amir David Nissan Cohen, Yoav Goldberg

Traditional NER is limited to a fixed set of entity types (person, location, org). But what if you want to find 'renewable energy companies' or 'neurodegenerative diseases' in text? NERetrieve reframes NER as an open-ended retrieval problem — given any free-text entity type description, retrieve matching entities from a document. We release a large-scale dataset and benchmarks for this task.

What's in your Head? Emergent Behaviour in Multi-Task Transformer Models
EMNLP 2021

What's in your Head? Emergent Behaviour in Multi-Task Transformer Models

Mor Geva, Uri Katz, Aviv Ben-Arie, Jonathan Berant

When a transformer is trained on multiple tasks at once, what happens inside its attention heads? We find that heads naturally specialize — some become task-specific experts, others learn shared representations, and some go dormant. This work provides a systematic analysis of how multi-task learning shapes the internal structure of transformers, revealing emergent division of labor that no one explicitly designed.

Academic Journey

2022 — Present

PhD in Computer Science

Bar-Ilan University

Advisor: Prof. Yoav Goldberg

2020 — 2022

M.Sc in Computer Science

Tel Aviv University

Advisor: Prof. Jonathan Berant

2017 — 2020

M.Sc in Computational Neuroscience

Weizmann Institute of Science

Advisor: Prof. Rony Paz