| USR: An unsupervised and reference free evaluation metric for dialog generation S Mehri, M Eskenazi arXiv preprint arXiv:2005.00456, 2020 | 295 | 2020 |
| Unsupervised evaluation of interactive dialog with DialoGPT S Mehri, M Eskenazi arXiv preprint arXiv:2006.12719, 2020 | 232 | 2020 |
| Dialoglue: A natural language understanding benchmark for task-oriented dialogue S Mehri, M Eric, D Hakkani-Tur arXiv preprint arXiv:2009.13570, 2020 | 158 | 2020 |
| A comprehensive assessment of dialog evaluation metrics YT Yeh, M Eskenazi, S Mehri arXiv preprint arXiv:2106.03706, 2021 | 132 | 2021 |
| Structured fusion networks for dialog S Mehri, T Srinivasan, M Eskenazi arXiv preprint arXiv:1907.10016, 2019 | 114 | 2019 |
| InstructDial: Improving zero and few-shot generalization in dialogue through instruction tuning P Gupta, C Jiao, YT Yeh, S Mehri, M Eskenazi, JP Bigham arXiv preprint arXiv:2205.12673, 2022 | 108 | 2022 |
| Investigating evaluation of open-domain dialogue systems with human generated multiple references P Gupta, S Mehri, T Zhao, A Pavel, M Eskenazi, JP Bigham arXiv preprint arXiv:1907.10568, 2019 | 104 | 2019 |
| Pretraining methods for dialog context representation learning S Mehri, E Razumovskaia, T Zhao, M Eskenazi arXiv preprint arXiv:1906.00414, 2019 | 102 | 2019 |
| Overview of the Ninth Dialog System Technology Challenge: DSTC9 C Gunasekara, S Kim, LF D’Haro, A Rastogi, YN Chen, M Eric, ... IEEE/ACM Transactions on Audio, Speech, and Language Processing 32, 4066-4076, 2024 | 96* | 2024 |
| Chat disentanglement: Identifying semantic reply relationships with random forests and recurrent neural networks S Mehri, G Carenini Proceedings of the Eighth International Joint Conference on Natural Language …, 2017 | 62 | 2017 |
| Star: A schema-guided dialog dataset for transfer learning JEM Mosig, S Mehri, T Kober arXiv preprint arXiv:2010.11853, 2020 | 47 | 2020 |
| Example-driven intent prediction with observers S Mehri, M Eric Proceedings of the 2021 Conference of the North American Chapter of the …, 2021 | 45 | 2021 |
| Report from the nsf future directions workshop on automatic evaluation of dialog: Research directions and challenges S Mehri, J Choi, LF D'Haro, J Deriu, M Eskenazi, M Gasic, K Georgila, ... arXiv preprint arXiv:2203.10012, 2022 | 39 | 2022 |
| Anchored preference optimization and contrastive revisions: Addressing underspecification in alignment K D'Oosterlinck, W Xu, C Develder, T Demeester, A Singh, C Potts, ... Transactions of the Association for Computational Linguistics 13, 442-460, 2025 | 32 | 2025 |
| LAD: Language models as data for zero-shot dialog S Mehri, Y Altun, M Eskenazi arXiv preprint arXiv:2207.14393, 2022 | 24 | 2022 |
| Middle-out decoding S Mehri, L Sigal Advances in Neural Information Processing Systems 31, 2018 | 24 | 2018 |
| Data-efficient alignment of large language models with human feedback through natural language D Jin, S Mehri, D Hazarika, A Padmakumar, S Lee, Y Liu, M Namazifar arXiv preprint arXiv:2311.14543, 2023 | 22 | 2023 |
| Gensf: Simultaneous adaptation of generative pre-trained models and slot filling S Mehri, M Eskenazi arXiv preprint arXiv:2106.07055, 2021 | 19 | 2021 |
| Schema-guided paradigm for zero-shot dialog S Mehri, M Eskenazi arXiv preprint arXiv:2106.07056, 2021 | 18 | 2021 |
| Lmunit: Fine-grained evaluation with natural language unit tests J Saad-Falcon, R Vivek, W Berrios, NS Naik, M Franklin, B Vidgen, ... arXiv preprint arXiv:2412.13091, 2024 | 16 | 2024 |
Maxine EskenaziPrincipal Systems Scientist, Carnegie Mellon UniversityVerified email at cs.cmu.edu
