Yonatan Belinkov
 | This article appears to have been generated by a large language model (such as ChatGPT) without having been rigorously scrutinized for verifiability, neutrality, original research, and copyright compliance. It may include misleading or inaccurate claims and fake references that sound plausible. (May 2026) (Learn how and when to remove this template message) |
| Yonatan Belinkov | |
|---|---|
| Born | |
| 🎓 Alma mater | Massachusetts Institute of Technology (PhD) Tel Aviv University (BSc, MA) |
| 💼 Occupation | |
| Known for | Research on neural language model interpretability, robustness and controllability |
| 🌐 Website | belinkov |
Yonatan Belinkov is a computer scientist whose research focuses on natural language processing, machine learning and artificial intelligence. He is an associate professor in the Henry and Marilyn Taub Faculty of Computer Science at the Technion – Israel Institute of Technology.[1][2] During the 2025–2026 academic year, he was a visiting scholar at the Kempner Institute for the Study of Natural and Artificial Intelligence at Harvard University.[3]
Belinkov is known for work on the analysis and interpretation of neural language models, including methods for probing, understanding and modifying internal representations in neural networks and large language models.[4][5] His research has addressed model interpretability, robustness, controllability, multilingual natural language processing and the behavior of language models under noise or factual intervention.[6]
Education and career
Belinkov received a BSc and an MA from Tel Aviv University in mathematics and Arabic and Islamic studies. He received a PhD in electrical engineering and computer science from the Massachusetts Institute of Technology in 2018.[3]
After completing his doctorate, Belinkov was a postdoctoral fellow at the Harvard John A. Paulson School of Engineering and Applied Sciences and a postdoctoral associate at the MIT Computer Science and Artificial Intelligence Laboratory.[3] He joined the Technion faculty in 2020.[7] In 2026, the Azrieli Foundation reported that Belinkov, an Azrieli Early Career Faculty Fellow in 2020–2021, had been promoted to associate professor at the Technion's Taub Faculty of Computer Science.[2]
Research
Belinkov's research has examined how neural language systems encode linguistic information and how their internal representations can be analyzed or controlled. In work reported by MIT News in 2017, Belinkov and collaborators studied the layers of neural machine translation and speech-recognition systems, finding that lower layers tended to encode lower-level linguistic information while higher layers captured more abstract properties.[8]
In 2019, MIT News covered work by Belinkov and collaborators on identifying neurons associated with linguistic features in neural machine translation systems. The study described methods for ranking and ablating neurons to analyze the contribution of particular internal units to translation behavior, including phenomena such as number and gender features.[4]
Belinkov has also published on the robustness of neural machine translation. His 2018 paper with Yonatan Bisk, Synthetic and Natural Noise Both Break Neural Machine Translation, argued that neural translation systems could be brittle when faced with synthetic and naturally occurring noise, and evaluated training approaches intended to improve robustness.[9]
A strand of Belinkov's later work has focused on large language models. He was a co-author of Locating and Editing Factual Associations in GPT, a 2022 NeurIPS paper (i.e., "The Rome paper") that proposed methods for identifying and editing factual associations in autoregressive transformer language models.[10] His subsequent research has included work on interpreting hallucinations and internal truthfulness representations in large language models.[11]
In 2024, Belinkov received a European Research Council Starting Grant for the project Control-LM: Controlling Large Language Models, which aims to develop methods for understanding and controlling the internal mechanisms of large language models.[5][12]
Awards and honors
- Harvard Mind, Brain, and Behavior Postdoctoral Fellowship.[6]
- Azrieli Early Career Faculty Fellowship.[2]
- European Research Council Starting Grant, 2024, for Control-LM: Controlling Large Language Models.[5][12]
- Best Paper Award at EMNLP 2024 for Backward Lens: Projecting Language Model Gradients into the Vocabulary Space, co-authored with Shahar Katz, Mor Geva and Lior Wolf.[13]
- Krill Prize for Excellence in Scientific Research, 2025, awarded by the Wolf Foundation.[7]
Selected publications
- Belinkov, Yonatan; Durrani, Nadir; Dalvi, Fahim; Sajjad, Hassan; Glass, James (2017). What do Neural Machine Translation Models Learn about Morphology?. Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics. pp. 861–872. doi:10.18653/v1/P17-1080. Retrieved 29 April 2026.
- Belinkov, Yonatan; Bisk, Yonatan (2018). Synthetic and Natural Noise Both Break Neural Machine Translation. International Conference on Learning Representations. Retrieved 29 April 2026.
- Belinkov, Yonatan; Glass, James (2019). "Analysis Methods in Neural Language Processing: A Survey". Transactions of the Association for Computational Linguistics. 7: 49–72. doi:10.1162/tacl_a_00254. Retrieved 29 April 2026.
- Belinkov, Yonatan (2022). "Probing Classifiers: Promises, Shortcomings, and Advances". Computational Linguistics. 48 (1): 207–219. doi:10.1162/coli_a_00422. Retrieved 29 April 2026.
- Meng, Kevin; Bau, David; Andonian, Alex J.; Belinkov, Yonatan (2022). Locating and Editing Factual Associations in GPT. Advances in Neural Information Processing Systems. Retrieved 29 April 2026.
- Katz, Shahar; Belinkov, Yonatan; Geva, Mor; Wolf, Lior (2024). Backward Lens: Projecting Language Model Gradients into the Vocabulary Space. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing. pp. 2390–2422. doi:10.18653/v1/2024.emnlp-main.142. Retrieved 29 April 2026.
- Orgad, Hadas; Toker, Michael; Gekhman, Zorik; Reichart, Roi; Szpektor, Idan; Kotek, Hadas; Belinkov, Yonatan (2025). LLMs Know More Than They Show: On the Intrinsic Representation of LLM Hallucinations. International Conference on Learning Representations. Retrieved 29 April 2026.
References
- ↑ "Yonatan Belinkov". Technion Research Portal. Technion – Israel Institute of Technology. Retrieved 29 April 2026.
- ↑ 2.0 2.1 2.2 "Fellows' Appointment, Promotions, and Achievements – Spring 2026". The Azrieli Foundation. 3 March 2026. Retrieved 29 April 2026.
- ↑ 3.0 3.1 3.2 "Yonatan Belinkov". Kempner Institute for the Study of Natural and Artificial Intelligence. Harvard University. Retrieved 29 April 2026.
- ↑ 4.0 4.1 Matheson, Rob (1 February 2019). "Putting neural networks under the microscope". MIT News. Retrieved 29 April 2026.
- ↑ 5.0 5.1 5.2 "Four Technion Researchers Receive ERC Starting Grants". Technion – Israel Institute of Technology. 5 September 2024. Retrieved 29 April 2026.
- ↑ 6.0 6.1 "Dr. Yonatan Belinkov". T3 Technion Technology Transfer. Technion Research & Development Foundation. Retrieved 29 April 2026.
- ↑ 7.0 7.1 "Two Technion Faculty Members Win the Krill Prize". Technion – Israel Institute of Technology. 21 May 2025. Retrieved 29 April 2026.
- ↑ Hardesty, Larry (10 December 2017). "Reading a neural network's mind". MIT News. Retrieved 29 April 2026.
- ↑ Belinkov, Yonatan; Bisk, Yonatan (2018). Synthetic and Natural Noise Both Break Neural Machine Translation. International Conference on Learning Representations. Retrieved 29 April 2026.
- ↑ Meng, Kevin; Bau, David; Andonian, Alex J.; Belinkov, Yonatan (2022). Locating and Editing Factual Associations in GPT. Advances in Neural Information Processing Systems. Retrieved 29 April 2026.
- ↑ Orgad, Hadas; Toker, Michael; Gekhman, Zorik; Reichart, Roi; Szpektor, Idan; Kotek, Hadas; Belinkov, Yonatan (2025). LLMs Know More Than They Show: On the Intrinsic Representation of LLM Hallucinations. International Conference on Learning Representations. Retrieved 29 April 2026.
- ↑ 12.0 12.1 "EuroTech researchers win 17 ERC Starting Grants". EuroTech Universities Alliance. 6 September 2024. Retrieved 29 April 2026.
- ↑ Katz, Shahar; Belinkov, Yonatan; Geva, Mor; Wolf, Lior (2024). Backward Lens: Projecting Language Model Gradients into the Vocabulary Space. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing. pp. 2390–2422. doi:10.18653/v1/2024.emnlp-main.142. Retrieved 29 April 2026.
External links
- Official website
- Yonatan Belinkov at the Technion Research Portal
- Yonatan Belinkov at the Kempner Institute
This article "Yonatan Belinkov" is from Wikipedia. The list of its authors can be seen in its historical and/or the page Edithistory:Yonatan Belinkov. Articles copied from Draft Namespace on Wikipedia could be seen on the Draft Namespace of Wikipedia and not main one.
