| A Distributional Approach to Controlled Text Generation M Khalifa, H Elsahar, M Dymetman ICLR, 2020 | 130 | 2020 |
| Character Convolutions for Arabic Named Entity Recognition with Long Short-Term Memory Networks M Khalifa, K Shaalan Computer Speech & Language 58, 335-346, 2019 | 69 | 2019 |
| GRACE: Discriminator-Guided Chain-of-Thought Reasoning M Khalifa, L Logeswaran, M Lee, H Lee, L Wang EMNLP Findings, 2023 | 38* | 2023 |
| Ensemble Learning for Irony Detection in Arabic Tweets M Khalifa, N Hussein FIRE (Working Notes), 433-438, 2019 | 31 | 2019 |
| A Bag of Tricks for Dialogue Summarization M Khalifa, M Ballesteros, K Mckeown EMNLP, 2021 | 29 | 2021 |
| Extracting Synonyms from Bilingual Dictionaries M Jarrar, E Karajah, M Khalifa, K Shaalan Global Wordnet Conference 2021, 2020 | 26 | 2020 |
| Merging Generated and Retrieved Knowledge for Open-Domain QA Y Zhang, M Khalifa, L Logeswaran, M Lee, H Lee, L Wang EMNLP, 2023 | 25 | 2023 |
| Has It All Been Solved? Open NLP Research Questions Not Solved by Large Language Models O Ignat, Z Jin, A Abzaliev, L Biester, S Castro, N Deng, X Gao, A Gunal, ... LREC-COLING 2024, 2023 | 23* | 2023 |
| BOLT: Fast Energy-based Controlled Text Generation with Tunable Biases X Liu, M Khalifa, L Wang ACL, 2023 | 16 | 2023 |
| Few-shot Reranking for Multi-hop QA via Language Model Prompting M Khalifa, L Logeswaran, M Lee, H Lee, L Wang ACL, 2022 | 16* | 2022 |
| Self-training pre-trained language models for zero-and few-shot multi-dialectal Arabic sequence labeling M Khalifa, M Abdul-Mageed, K Shaalan EACL, 2021 | 16 | 2021 |
| Source-Aware Training Enables Knowledge Attribution in Language Models M Khalifa, D Wadden, E Strubell, H Lee, L Wang, I Beltagy, H Peng COLM, 2024 | 14 | 2024 |
| LitCab: Lightweight Calibration of Language Models on Outputs of Varied Lengths X Liu, M Khalifa, L Wang ICLR, 2023 | 12* | 2023 |
| Small Language Models Need Strong Verifiers to Self-Correct Reasoning Y Zhang, M Khalifa, L Logeswaran, J Kim, M Lee, H Lee, L Wang ACL Findings, 2024 | 8 | 2024 |
| Exploring Demonstration Ensembling for In-context Learning M Khalifa, L Logeswaran, M Lee, H Lee, L Wang ICLR Workshop on Mathematical and Empirical Understanding of Foundation Models, 2023 | 5 | 2023 |
| Method and system for controlling distributions of attributes in language models for text generation M Dymetman, H Elsahar, M Khalifa US Patent App. 17/391,178, 2022 | 3 | 2022 |
| Book Success Prediction with Pretrained Sentence Embeddings and Readability Scores M Khalifa, A Islam Proceedings of the 55th Hawaii International Conference on System Sciences, 2022 | 3* | 2022 |
| Factcheckmate: Preemptively detecting and mitigating hallucinations in lms D Alnuhait, N Kirtane, M Khalifa, H Peng arXiv preprint arXiv:2410.02899, 2024 | 2 | 2024 |
| Contrastive Training Improves Zero-Shot Classification of Semi-structured Documents M Khalifa, Y Vyas, S Wang, G Horwood, S Mallya, M Ballesteros ACL Findings, 2022 | 2 | 2022 |
| Learning to Reason via Program Generation, Emulation, and Search N Weir*, M Khalifa*, L Qiu, O Weller, P Clark NeurIPS, 2024 | 1 | 2024 |
Lu WangAssociate Professor, Computer Science and Engineering, University of MichiganVerified email at umich.edu