Shaden Shaar

RESEARCH INTERESTS

Natural Language Processing for complex textual analysis, specializing in long-form text generation and evaluation. My current work explores narrative summarization and document-level question answering, with an emphasis on maintaining semantic coherence across extended passages. Previously, I developed automated fact-checking systems and detection mechanisms for propaganda in multi-length documents, contributing to information integrity in digital content.

EDUCATION

• 2021 — present
  PhD, Computer Science

  Cornell University · Ithaca, NY

  Minor: Applied Mathematics
• 2021 — 2024
  M.S., Computer Science

  Cornell University · Ithaca, NY
• 2015 — 2019
  B.S., Computer Science

  Carnegie Mellon University · Doha, Qatar

  Minor: Mathematics · University Honors

EXPERIENCE

• May 2025 — Aug 2025
  Applied Scientist Intern

  Zillow Group · Remote
• Jan 2025 — May 2025
  Machine Learning Research Engineer Intern

  Scale AI · Remote
• May 2022 — Aug 2022
  AI/ML Research Intern

  Apple · Cupertino, CA
• Jul 2019 — Aug 2021
  Research Assistant

  Qatar Computing Research Institute, HBKU · Doha, Qatar
• May 2018 — Aug 2018
  Research Intern

  Robotics Institute, Carnegie Mellon University · Pittsburgh, PA
• May 2017 — Jun 2018
  Part-Time Research Assistant

  Carnegie Mellon University · Doha, Qatar

TEACHING

Cornell University

• Fall 2022
  CS 4740: Natural Language Processing
• Spring 2022
  Introduction to Machine Learning

Carnegie Mellon University

• Fall 2018 & Spring 2019
  11-785: Introduction to Deep Learning
• Spring 2018 & Spring 2019
  15-251: Great Theoretical Ideas in Computer Science
• Fall 2017
  15-213: Introduction to Computer Systems
• Fall 2016 & Fall 2017
  15-112: Fundamentals of Programming
• Spring 2016
  21-127: Concepts of Mathematics

• Thematic Analysis of Accepted Exception Requests for Heart Transplant Candidates Using a Large Language Model
  JHLT · 2026
• MovieRecapsQA: A Multimodal Open-Ended Video Question-Answering Benchmark
  CVPR · 2026
• Are Triggers Needed for Document-Level Event Extraction?
  TACL · 2025 · 2 citations
• Pungene at DialAM-2024: Identification of Propositional and Illocutionary Relations
  ArgMining · 2024 · 2 citations
• Edward Said at Touché: Human Value Detection Using Transformers and Upsampling
  CLEF · 2024 · 1 citations
• A Survey on Multimodal Disinformation Detection
  COLING · 2022 · 224 citations
• Overview of the CLEF–2022 CheckThat! Lab on Fighting the COVID-19 Infodemic and Fake News Detection
  CLEF · 2022 · 90 citations
• The CLEF-2022 CheckThat! Lab on Fighting the COVID-19 Infodemic and Fake News Detection
  ECIR · 2022 · 88 citations
• Overview of the CLEF-2022 CheckThat! Lab Task 1 on Identifying Relevant Claims in Tweets
  CEUR · 2022 · 83 citations
• Assisting the Human Fact-Checkers: Detecting All Previously Fact-Checked Claims in a Document
  EMNLP · 2022 · 45 citations

AWARDS & HONORS

• 2021
  University Fellowship, Cornell University — for exceptional preparation and promise.
• 2020
  Best Demo Award, Honorable Mention, ACL 2020 — for the Prta propaganda-analysis system.
• 2019
  University Honors, Carnegie Mellon University — for outstanding GPA.
• 2017
  Dean's List, Carnegie Mellon University — F15, S16, F16, F17.
• 2015
  50% Academic Merit Scholarship, Carnegie Mellon University.