🧑‍🔬 Asaf Yehudai

🏛️ Affiliations

🎓Hebrew University of JerusalemJerusalem · Israel2018–2026 · 34 papersEducation since 2018 · The Rachel and Selim Benin School of Engineering and Computer ScienceEmployment since 2019 · Computer sciencecurrent🏢IBMArmonk · United States2022–2026 · 26 paperscurrent🔬IBM Research - HaifaHaifa · Israel2022–2024 · 2 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 1 more institution on single bylines are not listed.

🧭 Fields, topics and concepts

Of its works in our library, with the number of works on each.

📅 Works by year

2020s

📄 Papers

The most cited first (OpenAlex and our library).

1. Filling the Gaps in Ancient Akkadian Texts: A Masked Language Modelling Approach (2021 · 30 citations)
   Editors of damaged cuneiform tablets fill broken parts from context, and the authors treat this as masked language modelling over Oracc transliterations (about 1M words, 2.3M signs).
2. A Survey on Evaluation of LLM-based Agents (2026 · 21 citations)
   LLM-based agents pair a backbone model with a harness that adds tools, memory and multi-step control. Because of this, scoring only their text output no longer captures what they can do. The authors present what they call the first comprehensive survey of how such agents are evaluated. They organize the field from…
3. JuStRank: Benchmarking LLM Judges for System Ranking (2025 · 15 citations)
   LLM judges are usually validated on individual responses or response pairs, without regard to which system produced them.
4. The Mighty ToRR: A Benchmark for Table Reasoning and Robustness in LLMs (2026 · 1 citation)
   Large language models are often given tables, yet it is unclear how well they reason over them and how much their answers depend on how a table is written out.
5. Will it Merge? On The Causes of Model Mergeability (2026)
   Merging combines several fine-tuned models into one multitask model without retraining, yet it is unclear why some fine-tuned updates survive merging better than others.

All works

11 works of theirs in our library, the most cited first; 5 with a page here, the others link their original until we summarise them.

1. Filling the Gaps in Ancient Akkadian Texts: A Masked Language Modelling ApproachKoren Lazar, Benny Saret, Asaf Yehudai, et al.Semitic languages · 30 citations
2. A Survey on Evaluation of LLM-based AgentsFindings of the Association for Computational LinguisticsAsaf Yehudai, Lilach Eden, Alan Li, et al.2026 · 21 citations
3. JuStRank: Benchmarking LLM Judges for System RankingAnnual Meeting of the Association for Computational Linguistics (ACL)Ariel Gera, Odellia Boni, Yotam Perlitz, et al.2025 · 15 citations
4. The Mighty ToRR: A Benchmark for Table Reasoning and Robustness ↗arXiv (Cornell University) · no summary yetShir Ashury-Tahan et al.2025 · 10 citations
5. Evaluating and Improving the Coreference Capabilities of Machine Translation Models ↗Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics · no summary yetAsaf Yehudai et al.2023 · 2 citations
6. The Mighty ToRR: A Benchmark for Table Reasoning and Robustness in LLMsWorkshop on Structured Understanding, Retrieval, and Generation in the LLM EraShir Ashury-Tahan, Yifan Mai, Rajmohan C, et al.2026 · 1 citation
7. Will it Merge? On The Causes of Model MergeabilityFindings of the Association for Computational LinguisticsAdir Rahamim, Asaf Yehudai, Boaz Carmeli, et al.2026
8. Position: Agentic Systems Should be General ↗SSRN Electronic Journal · no summary yetElron Bandel et al.2026
9. Mediocrity is the key for LLM as a Judge Anchor Selection ↗Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · no summary yetShachar Don-Yehiya et al.2026
10. Agentic CLEAR: Automating Multi-Level Evaluation of LLM Agents ↗Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations) · no summary yetAsaf Yehudai, Lilach Eden, Michal Shmueli-Scheuer2026
11. Teaching Values to Machines: Simulating Human-Like Behavior in LLMs ↗Proceedings of the Fifth Workshop on Generation, Evaluation and Metrics (GEM) · no summary yetAsaf Yehudai, Naama Rozen, Ariel Gera2026

🤝 Co-authors here

12 of 16 co-authors with a page, the most papers together first.

• Ariel Gera ×2
• Leshem Choshen ×2
• Lilach Eden ×2
• Michal Shmueli-Scheuer ×2
• Roy Bar-Haim ×2
• Yotam Perlitz ×2
• Alan Li
• Arman Cohan
• Elron Bandel
• Gabriel Stanovsky
• Koren Lazar
• Percy Liang

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

• Annual Meeting of the Association for Computational Linguistics (ACL) ×3: ACL 2025
• Findings of the Association for Computational Linguistics ×2: Findings of the Association for Computational Linguistics 2026 ×2
• Conference on Empirical Methods in Natural Language Processing (EMNLP): EMNLP 2021
• Workshop on Structured Understanding, Retrieval, and Generation in the LLM Era: Workshop on Structured Understanding, Retrieval, and Generation in the LLM Era 2026
• Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics
• Proceedings of the Fifth Workshop on Generation, Evaluation and Metrics (GEM)
• SSRN Electronic Journal

🔗 Cited by

Papers of our library cite their works 37 times (of the 149,439 papers whose bibliographies we read); 7 citing papers with a page here →.

Updated 1 November 2026

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/authors/asaf-yehudai/