| Gemini 2.5: Pushing the frontier with advanced reasoning, multimodality, long context, and next generation agentic capabilities G Comanici, E Bieber, M Schaekermann, I Pasupat, N Sachdeva, I Dhillon, ... arXiv preprint arXiv:2507.06261, 2025 | 1337 | 2025 |
| Towards faithfully interpretable NLP systems: How should we define and evaluate faithfulness? A Jacovi, Y Goldberg arXiv preprint arXiv:2004.03685, 2020 | 886 | 2020 |
| Formalizing Trust in Artificial Intelligence: Prerequisites, Causes and Goals of Human Trust in AI A Jacovi, A Marasović, T Miller, Y Goldberg Proceedings of the 2021 ACM Conference on Fairness, Accountability, and …, 2021 | 818 | 2021 |
| Understanding Convolutional Neural Networks for Text Classification A Jacovi, OS Shalom, Y Goldberg Proceedings of the Workshop: BlackboxNLP@EMNLP 2018, 2018 | 365 | 2018 |
| Amnesic probing: Behavioral explanation with amnesic counterfactuals Y Elazar, S Ravfogel, A Jacovi, Y Goldberg Transactions of the Association for Computational Linguistics 9, 160-175, 2021 | 294 | 2021 |
| Contrastive explanations for model interpretability A Jacovi, S Swayamdipta, S Ravfogel, Y Elazar, Y Choi, Y Goldberg arXiv preprint arXiv:2103.01378, 2021 | 152 | 2021 |
| Aligning Faithful Interpretations with their Social Attribution A Jacovi, Y Goldberg Transactions of the Association for Computational Linguistics 9, 294-310, 2021 | 137 | 2021 |
| Stop uploading test data in plain text: Practical strategies for mitigating data contamination by evaluation benchmarks A Jacovi, A Caciularu, O Goldman, Y Goldberg arXiv preprint arXiv:2305.10160, 2023 | 116 | 2023 |
| Neural network gradient-based learning of black-box function interfaces A Jacovi, G Hadash, E Kermany, B Carmeli, O Lavi, G Kour, J Berant 7th International Conference on Learning Representations, ICLR 2019, 2019 | 95* | 2019 |
| Human interpretation of saliency-based explanation over text H Schuff, A Jacovi, H Adel, Y Goldberg, NT Vu Proceedings of the 2022 ACM conference on fairness, accountability, and …, 2022 | 55 | 2022 |
| A chain-of-thought is as strong as its weakest link: A benchmark for verifiers of reasoning chains A Jacovi, Y Bitton, B Bohnet, J Herzig, O Honovich, M Tseng, M Collins, ... arXiv preprint arXiv:2402.00559, 2024 | 43 | 2024 |
| The FACTS Grounding Leaderboard: Benchmarking LLMs' Ability to Ground Responses to Long-Form Input A Jacovi, A Wang, C Alberti, C Tao, J Lipovetz, K Olszewska, L Haas, ... arXiv preprint arXiv:2501.03200, 2025 | 39 | 2025 |
| Diagnosing AI explanation methods with folk concepts of behavior A Jacovi, J Bastings, S Gehrmann, Y Goldberg, K Filippova Journal of Artificial Intelligence Research 78, 459-489, 2023 | 35 | 2023 |
| Exposing shallow heuristics of relation extraction models with challenge data S Rosenman, A Jacovi, Y Goldberg arXiv preprint arXiv:2010.03656, 2020 | 35 | 2020 |
| Is it really long context if all you need is retrieval? towards genuinely difficult long context nlp O Goldman, A Jacovi, A Slobodkin, A Maimon, I Dagan, R Tsarfaty arXiv preprint arXiv:2407.00402, 2024 | 29 | 2024 |
| Trends in explainable AI (XAI) literature A Jacovi arXiv preprint arXiv:2301.05433, 2023 | 29 | 2023 |
| Unpacking human-AI interaction in safety-critical industries: a systematic literature review TA Bach, JK Kristiansen, A Babic, A Jacovi IEEE Access, 2024 | 28 | 2024 |
| Learning and Understanding Different Categories of Sexism Using Convolutional Neural Network’s Filters S Sharifirad, A Jacovi, S Matwin Proceedings of the 2019 Workshop on Widening NLP, 21-23, 2019 | 26 | 2019 |
| Data contamination report from the 2024 CONDA shared task O Sainz, I García-Ferrero, A Jacovi, JA Campos, Y Elazar, E Agirre, ... Proceedings of the 1st Workshop on Data Contamination (CONDA), 41-56, 2024 | 14 | 2024 |
| A comprehensive evaluation of tool-assisted generation strategies A Jacovi, A Caciularu, J Herzig, R Aharoni, B Bohnet, M Geva arXiv preprint arXiv:2310.10062, 2023 | 13 | 2023 |
Yoav GoldbergProfessor, Bar Ilan University. Research Director, AI2-IsraelVerified email at cs.biu.ac.il
