Improving Argument Saliency Coverage in Small LLMs for Long Legal Opinion Summarization via Sequence-Level Distillation
About
Welcome! I recently defended my PhD in the Computer Science Department at the University of Pittsburgh, with research spanning Computational Argumentation and Text Summarization, with applications in legal and educational domains.
I received my M.Sc. from Cairo University (advisor: Mohsen Rashwan). I have held research internships at TikTok/ByteDance (SAMI) and Microsoft (ROAR).
News
- Aug 2026: Defended my PhD! Thank you to my advisor, Diane Litman, and my committee: Kathleen McKeown, Xiang Lorraine Li, and Adriana Kovashka. Joined Zillow Group as a Senior Applied Scientist.
- Aug 2026: One paper accepted to EMNLP 2026 Main Conference - see you in Budapest, Hungary 🇭🇺
- Now: My research interests include Computational Argumentation, Text Summarization, and reliable NLP systems for high-stakes domains. My research statement is available here.
- May 2026: Awarded the Outstanding Reviewer Award from EACL 2026 🎉
- Jan 2026: Awarded LRDC Council Award to support my research for the third consecutive year 🎉
- JAN 2026: One paper accepted at EACL 2026 🎉 see you in Morocco 🇲🇦
- Dec 2025: Co-organizing ArgMining@ACL 2026
- Nov 2025: My internship paper at Zillow SynClaimEval has been accepted to appear at Eval4NLP @ AACL2025 🎉
- Aug 2025: I received the CS50 fellowship (awarded to two PhD students across the computer science department) 🎉
- May 2025: One paper accepted at BEA @ ACL 2025 🎉
- May 2025: Joining Zillow Group as an Applied Scientist Intern.
- Apr 2025: Passed proposal defense (Committee: Diane Litman, Kathleen McKeown, Xiang Lorraine Li, Adriana Kovashka).
- Sep 2024: EMNLP 2024 (Findings) acceptance — see you in Miami 🌴
- May 2024: Started internship at Microsoft ROAR; Apr 2024: Passed Oral Comprehensive Exam.
- Oct 2023: ImageArg overview paper out; co-organized ArgMining 2023 shared task.
Research Agenda
I develop argument-aware generation and evaluation methods for long documents. My my work aims to build faithful, interpretable, and reliable NLP systems for high-stakes domains.
Selected Publications
ARC: Argument Representation and Coverage Analysis for Zero-Shot Long Document Summarization with Instruction Following LLMs
Show BibTeX
@article{elaraby2025arc,
title = {ARC: Argument Representation and Coverage Analysis for Zero-Shot Long Document Summarization with Instruction Following LLMs},
author = {Elaraby, Mohamed and Litman, Diane},
journal = {arXiv preprint arXiv:2505.23654},
year = {2025},
note = {Accepted at EACL 2026 Main Conference}
}
Lessons Learned in Assessing Student Reflections with LLMs
Show BibTeX
@inproceedings{elaraby-litman-2025-lessons,
author = {Elaraby, Mohamed and Litman, Diane},
title = {Lessons Learned in Assessing Student Reflections with LLMs},
booktitle = {Proceedings of the 20th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2025)},
year = {2025}
}
Persuasiveness of Generated Free-Text Rationales in Subjective Decisions: A Case Study on Pairwise Argument Ranking
Show BibTeX
@inproceedings{elaraby-etal-2024-persuasiveness,
author = {Elaraby, Mohamed and Litman, Diane and Li, Xiang Lorraine and Magooda, Ahmed},
title = {Persuasiveness of Generated Free-Text Rationales in Subjective Decisions: A Case Study on Pairwise Argument Ranking},
booktitle = {Findings of the Association for Computational Linguistics: EMNLP 2024},
year = {2024}
}
Adding Argumentation into Human Evaluation of Long Document Abstractive Summarization: A Case Study on Legal Opinions
Show BibTeX
@inproceedings{elaraby-etal-2024-adding,
title = {Adding Argumentation into Human Evaluation of Long Document Abstractive Summarization: A Case Study on Legal Opinions},
author = {Elaraby, Mohamed and Xu, Huihui and Gray, Morgan and Ashley, Kevin and Litman, Diane},
booktitle = {Proceedings of the Fourth Workshop on Human Evaluation of NLP Systems (HumEval) @ LREC-COLING 2024},
year = {2024}
}
ReflectSumm: A Benchmark for Course Reflection Summarization
Show BibTeX
@inproceedings{elaraby-etal-2024-reflectsumm,
title = {ReflectSumm: A Benchmark for Course Reflection Summarization},
author = {Zhong, Yang and Elaraby, Mohamed and Litman, Diane and Butt, Ahmed Ashraf and Menekse, Muhsin},
booktitle = {Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)},
year = {2024}
}
Overview of ImageArg-2023: The First Shared Task in Multimodal Argument Mining
Show BibTeX
@inproceedings{liu-etal-2023-overview,
title = {Overview of ImageArg-2023: The First Shared Task in Multimodal Argument Mining},
author = {Liu, Zhexiong and Elaraby, Mohamed and Zhong, Yang and Litman, Diane},
booktitle = {Proceedings of the 10th Workshop on Argument Mining},
year = {2023}
}
Towards Argument-Aware Abstractive Summarization of Long Legal Opinions with Summary Reranking
Show BibTeX
@inproceedings{elaraby-etal-2023-towards,
title = {Towards Argument-Aware Abstractive Summarization of Long Legal Opinions with Summary Reranking},
author = {Elaraby, Mohamed and Zhong, Yang and Litman, Diane},
booktitle = {Findings of the Association for Computational Linguistics: ACL 2023},
year = {2023}
}
ArgLegalSumm: Improving Abstractive Summarization of Legal Documents with Argument Mining
Show BibTeX
@inproceedings{elaraby-litman-2022-arglegalsumm,
title = {ArgLegalSumm: Improving Abstractive Summarization of Legal Documents with Argument Mining},
author = {Elaraby, Mohamed and Litman, Diane},
booktitle = {Proceedings of the 29th International Conference on Computational Linguistics},
year = {2022}
}
Talks
Invite me for a talk on argument-aware summarization, long-context evaluation, or faithful generation. Get in touch.