🧑‍🔬 Yassine Benajiba

🏛️ Affiliations

🏢AmazonSeattle · United States2021–2025 · 19 papers🎓Universitat Politècnica de ValènciaValencia · Spain2007–2013 · 7 papers🏢Thomson ReutersNew York · United States2013–2020 · 6 papers🎓Columbia UniversityNew York · United States2009–2010 · 5 papers🎓Arizona State UniversityTempe · United States2023–2025 · 2 papers🎓University of SheffieldSheffield · United Kingdom2023 · 2 papers🏢PhilipsAmsterdam · Netherlands2012–2015 · 2 papers🏢OracleAustin · United States2025Employment since 2025 · Sr Director of Applied Science, AI

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 2 more institutions 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

2010s

2000s

📄 Papers

The most cited first (OpenAlex and our library).

1. Arabic Named Entity Recognition using Optimized Feature Sets (2008 · 156 citations)
   The paper addresses Arabic named entity recognition. Arabic has no capitalisation, omits short vowels and attaches clitics to words, so many surface forms are ambiguous and the data are sparse. The authors argue against one shared feature set for every NE class. Instead, they build a separate classifier for each…
2. Arabic Named Entity Recognition: Using Features Extracted from Noisy Data (2010 · 42 citations)
   Arabic NER is hard because of rich morphology and small hand-labelled corpora, so features that need many examples, like syntactic context, are hard to learn from gold data alone.
3. MemInsight: Autonomous Memory Augmentation for LLM Agents (2025 · 22 citations)
   LLM agents rely on long-term memory to give coherent, personalized answers. As stored interactions pile up, raw and unstructured memory becomes noisy and harder to search. MemInsight addresses this by having an LLM backbone enrich each memory entry automatically with attribute–value annotations, without a…
4. Arabic Word Segmentation for Better Unit of Analysis (2010 · 8 citations)
   Arabic builds words by stacking prefixes, a stem and suffixes, so raw whitespace tokens are very sparse. This hurts learning and retrieval. The authors build two segmenters on Weighted Finite State Transducers. One produces full morphological segmentation, splitting every affix including gender markers. The other…
5. Barriers to Discrete Reasoning with Transformers: A Survey Across Depth, Exactness, and Bandwidth (2026 · 3 citations)
   The survey asks why transformer models, despite strong results in language and vision, remain unreliable at exact symbolic work such as arithmetic, Boolean logic, parsing, and multi-step algorithmic composition.
6. MT-OSC: Path for LLMs that Get Lost in Multi-Turn Conversation (2026 · 3 citations)
   LLMs perform noticeably worse when a task's instructions and context are spread across several dialogue turns.
7. MEAV: Model Editing with Alignment Vectors for inference time LLM alignment in single and multidomain preference spectrum (2026 · 1 citation)
   The paper addresses the cost of adjusting LLM alignment after training. Methods like RLHF or DPO need retraining for every new preference setting, and many inference-time alternatives rely on a reward model at each step. The authors propose MEAV, which treats alignment as model editing in the spirit of Task…
8. Arabic Mention Detection: Toward Better Unit of Analysis (2010 · 1 citation)
   Arabic words often fuse conjunctions, articles, stems and pronoun suffixes, so the choice of token unit shapes how well a tagger generalises.

All works

22 works of theirs in our library, the most cited first; 8 with a page here, the others link their original until we summarise them.

1. Arabic Named Entity Recognition using Optimized Feature SetsConference on Empirical Methods in Natural Language Processing (EMNLP)Yassine Benajiba, Mona Diab, Paolo Rosso2008 · 156 citations
2. Instruction Tuning for Few-Shot Aspect-Based Sentiment Analysis ↗Proceedings of the 13th Workshop on Computational Approaches to Subjectivity, Sentiment, & Social Media Analysis · no summary yetSiddharth Varia et al.2023 · 58 citations
3. Arabic Named Entity Recognition: Using Features Extracted from Noisy DataAnnual Meeting of the Association for Computational Linguistics (ACL)Yassine Benajiba, Imed Zitouni, Mona Diab, et al.2010 · 42 citations
4. MemInsight: Autonomous Memory Augmentation for LLM AgentsConference on Empirical Methods in Natural Language Processing (EMNLP)Rana Salama, Jason Cai, Michelle Yuan, et al.2025 · 22 citations
5. Towards Long Context Hallucination Detection ↗Findings of the Association for Computational Linguistics: NAACL 2025 · no summary yetSiyi Liu et al.2025 · 18 citations
6. Arabic Word Segmentation for Better Unit of AnalysisLanguage Resources and Evaluation Conference (LREC)Yassine Benajiba, Imed Zitouni2010 · 8 citations
7. Open Domain Question Answering with Conflicting Contexts ↗Findings of the Association for Computational Linguistics: NAACL 2025 · no summary yetSiyi Liu et al.2025 · 7 citations
8. Can LLMs Narrate Tabular Data? An Evaluation Framework for Natural Language Representations of Text-to-SQL System Outputs ↗Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track · no summary yetJyotika Singh et al.2025 · 6 citations
9. From Instructions to Constraints: Language Model Alignment with Automatic Constraint Verification ↗arXiv (Cornell University) · no summary yetWang Fei et al.2024 · 5 citations
10. Barriers to Discrete Reasoning with Transformers: A Survey Across Depth, Exactness, and BandwidthConference of the European Chapter of the Association for Computational Linguistics (EACL)Michelle Yuan, Weiyi Sun, Amir H. Rezaeian, et al.2026 · 3 citations
11. MT-OSC: Path for LLMs that Get Lost in Multi-Turn ConversationFindings of the Association for Computational LinguisticsJyotika Singh, Fang Tu, Miguel Ballesteros, et al.2026 · 3 citations
12. Rethinking LLM Uncertainty: A Multi-Agent Approach to Estimating Black-Box Model Uncertainty ↗Findings of the Association for Computational Linguistics: EMNLP 2025 · no summary yetYu Feng et al.2025 · 3 citations
13. Characterizing and Measuring Linguistic Dataset Drift ↗Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · no summary yetTyler A. Chang et al.2023 · 2 citations
14. MEAV: Model Editing with Alignment Vectors for inference time LLM alignment in single and multidomain preference spectrumFindings of the Association for Computational LinguisticsSadat Shahriar, Zheng Qi, Nikolaos Pappas, et al.2026 · 1 citation
15. GSM-SEM: Benchmark and Framework for Generating Semantically Variant Augmentations ↗arXiv (Cornell University) · no summary yetJyotika Singh et al.2026 · 1 citation
16. DiffuMask: Diffusion Language Model for Token-level Prompt Pruning ↗arXiv (Cornell University) · no summary yetCaleb Zheng et al.2026 · 1 citation
17. Aligning to Constraints for Data-Efficient Language Model Customization ↗Findings of the Association for Computational Linguistics: NAACL 2025 · no summary yetFei Wang et al.2025 · 1 citation
18. Self-supervised Analogical Learning using Language Models ↗arXiv (Cornell University) · no summary yetBen Zhou et al.2025 · 1 citation
19. Taxonomy Expansion for Named Entity Recognition ↗Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing · no summary yetKarthikeyan K et al.2023 · 1 citation
20. Arabic Mention Detection: Toward Better Unit of AnalysisConference of the North American Chapter of the Association for Computational Linguistics (NAACL)Yassine Benajiba, Imed Zitouni2010 · 1 citation
21. JTPRO: A Joint Tool–Prompt Reflective Optimization Framework for Language Agents ↗Findings of the Association for Computational Linguistics: ACL 2026 · no summary yetSandip Ghoshal et al.2026
22. NewsQs: Multi-Source Question Generation for the Inquiring Mind ↗arXiv (Cornell University) · no summary yetAlyssa Hwang et al.2024

🤝 Co-authors here

12 of 20 co-authors with a page, the most papers together first.

• Imed Zitouni ×3
• Michelle Yuan ×3
• Jyotika Singh ×2
• Miguel Ballesteros ×2
• Mona Diab ×2
• Monica Sunkara ×2
• Paolo Rosso ×2
• Sandip Ghoshal ×2
• Weiyi Sun ×2
• Amir H. Rezaeian
• Anna Currey
• Dan Roth

Venues

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

• Conference on Empirical Methods in Natural Language Processing (EMNLP) ×3: EMNLP 2025, EMNLP 2008
• Findings of the Association for Computational Linguistics: NAACL 2025 ×3
• Annual Meeting of the Association for Computational Linguistics (ACL) ×2: ACL 2010
• Findings of the Association for Computational Linguistics ×2: Findings of the Association for Computational Linguistics 2026 ×2
• Conference of the European Chapter of the Association for Computational Linguistics (EACL): EACL 2026
• Language Resources and Evaluation Conference (LREC): LREC 2010
• Conference of the North American Chapter of the Association for Computational Linguistics (NAACL): NAACL 2010
• Findings of the Association for Computational Linguistics: ACL 2026
• Findings of the Association for Computational Linguistics: EMNLP 2025
• Proceedings of the 13th Workshop on Computational Approaches to Subjectivity, Sentiment, & Social Media Analysis
• Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track

🔗 Cited by

Papers of our library cite their works 118 times (of the 149,439 papers whose bibliographies we read); 46 citing papers with a page here →.

Updated 2 November 2026

↑ back to top

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