Research output per year
Research output per year
Personal profile
About Me
I am an assistant professor in the Department of Computer Science at Bar-Ilan University.
I work on Artificial Intelligence and Machine Learning, focusing on Interpretability, Data Attribution, and Evaluation of generative models (e.g., LLMs), to develop holistic, causal, and data-centric approaches to study how, when, and why such models work (and when they don't).
I was previously a postdoc at AI2 and at the University of Washington. I completed my PhD in Computer Science in the NLP lab at Bar-Ilan University.
Research
- Fields of Interest
- Interpretability
- Data Attribution
- Generative AI
- Machine Learning
- Natural Language Processing
Fingerprint
Dive into the research topics where Yanai Elazar is active. These topic labels come from the works of this person. Together they form a unique fingerprint.
- 1 Similar Profiles
Collaborations and top research areas from the last five years
Recent external collaboration on country/territory level. Dive into details by clicking on the dots or
-
Calibrating Large Language Models with Sample Consistency
Lyu, Q., Shridhar, K., Malaviya, C., Zhang, L., Elazar, Y., Tandon, N., Apidianaki, M., Sachan, M. & Callison-Burch, C., 11 Apr 2025, Special Track on AI Alignment. Walsh, T., Shah, J. & Kolter, Z. (eds.). 18 ed. Association for the Advancement of Artificial Intelligence, p. 19260-19268 9 p. (Proceedings of the AAAI Conference on Artificial Intelligence; vol. 39, no. 18).Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review
Open Access -
GENERALIZATION V.S. MEMORIZATION: TRACING LANGUAGE MODELS' CAPABILITIES BACK TO PRETRAINING DATA
Wang, X., Antoniades, A., Elazar, Y., Amayuelas, A., Albalak, A., Zhang, K. & Wang, W. Y., 2025, 13th International Conference on Learning Representations, ICLR 2025. International Conference on Learning Representations, ICLR, p. 46390-46410 21 p. (13th International Conference on Learning Representations, ICLR 2025).Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review
6 Scopus citations -
Hybrid Preferences: Learning to Route Instances for Human vs. AI Feedback
Miranda, L. J. V., Wang, Y., Elazar, Y., Kumar, S., Pyatkin, V., Brahman, F., Smith, N. A., Hajishirzi, H. & Dasigi, P., 2025, Long Papers. Che, W., Nabende, J., Shutova, E. & Pilehvar, M. T. (eds.). Association for Computational Linguistics (ACL), p. 7162-7200 39 p. (Proceedings of the Annual Meeting of the Association for Computational Linguistics; vol. 1).Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review
-
OLMOTRACE: Tracing Language Model Outputs Back to Trillions of Training Tokens
Liu, J., Blanton, T., Elazar, Y., Min, S., Chen, Y. S., Chheda-Kothary, A., Tran, H., Bischoff, B., Marsh, E., Schmitz, M., Trier, C., Sarnat, A., James, J., Borchardt, J., Kuehl, B., Cheng, E., Farley, K., Sreeram, S., Anderson, T. & Albright, D. & 11 others, , 2025, System Demonstrations. Mishra, P., Muresan, S. & Yu, T. (eds.). Association for Computational Linguistics (ACL), p. 178-188 11 p. (Proceedings of the Annual Meeting of the Association for Computational Linguistics; vol. 3).Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review
Open Access -
ON LINEAR REPRESENTATIONS AND PRETRAINING DATA FREQUENCY IN LANGUAGE MODELS
Merullo, J., Smith, N. A., Wiegreffe, S. & Elazar, Y., 2025, 13th International Conference on Learning Representations, ICLR 2025. International Conference on Learning Representations, ICLR, p. 31715-31739 25 p. (13th International Conference on Learning Representations, ICLR 2025).Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review
1 Scopus citations
Prizes
-
זכייה במלגת רוטשילד 2022-2023
Elazar, Y. (Recipient), Diamandi, H. (Recipient), Haim-Nachum, S. (Recipient) & Nachshoni, T. (Recipient), 2022
Prize: Scholarship