| Orca: Progressive learning from complex explanation traces of gpt-4 S Mukherjee, A Mitra, G Jawahar, S Agarwal, H Palangi, A Awadallah arXiv preprint arXiv:2306.02707, 2023 | 524 | 2023 |
| DeClarE: Debunking Fake News and False Claims using Evidence-Aware Deep Learning K Popat, S Mukherjee, A Yates, G Weikum EMNLP 2018, 2018 | 477 | 2018 |
| Where the truth lies: Explaining the credibility of emerging claims on the web and social media K Popat, S Mukherjee, J Strötgen, G Weikum WWW 2017, 1003-1012, 2017 | 335 | 2017 |
| AdaMix: Mixture-of-Adaptations for Parameter-efficient Model Tuning Y Wang, S Agarwal, S Mukherjee, X Liu, J Gao, AH Awadallah, J Gao EMNLP 2022, 2022 | 306* | 2022 |
| OpenTag: Open Attribute Value Extraction from Product Profiles [Deep Learning, Active Learning, Named Entity Recognition] G Zheng, S Mukherjee, XL Dong, F Li SIGKDD 2018, 2018 | 264* | 2018 |
| Uncertainty-aware Self-training for Few-shot Text Classification S Mukherjee, AH Awadallah NeurIPS 2020, 2020 | 261* | 2020 |
| Credibility assessment of textual claims on the web K Popat, S Mukherjee, J Strötgen, G Weikum CIKM 2016, 2173-2178, 2016 | 245 | 2016 |
| Hybrid LLM: Cost-Efficient and Quality-Aware Query Routing AHA D. Ding, A. Mallick, C. Wang, R. Sim, S. Mukherjee, V. Rühle, L.V. S ... ICLR 2024, 2024 | 203* | 2024 |
| Feature specific sentiment analysis for product reviews S Mukherjee, P Bhattacharyya Part 1, Lecture Notes in Computer Science, Springer 7181:475– 487, 475-487, 2012 | 191 | 2012 |
| Retrieval-augmented generation with graphs (graphrag) H Han, Y Wang, H Shomer, K Guo, J Ding, Y Lei, M Halappanavar, ... arXiv preprint arXiv:2501.00309, 2024 | 182 | 2024 |
| People on Drugs: Credibility of User Statements in Health Communities S Mukherjee, G Weikum, C Danescu-Niculescu-Mizil KDD 2014, 2014 | 167 | 2014 |
| Sentiment Analysis in Twitter with Lightweight Discourse Analysis S Mukherjee, P Bhattacharyya In Proceedings of COLING 2012, 2012 | 152 | 2012 |
| Leveraging joint interactions for credibility analysis in news communities S Mukherjee, G Weikum CIKM 2015, 353-362, 2015 | 141 | 2015 |
| Meta Self-training for Few-shot Neural Sequence Labeling Y Wang, S Mukherjee, H Chu, Y Tu, M Wu, J Gao, AH Awadallah SIGKDD 2021, 2020 | 130 | 2020 |
| Rewoo: Decoupling reasoning from observations for efficient augmented language models B Xu, Z Peng, B Lei, S Mukherjee, Y Liu, D Xu arXiv preprint arXiv:2305.18323, 2023 | 119* | 2023 |
| XtremeDistil: Multi-stage Distillation for Massive Multilingual Models S Mukherjee, A Awadallah ACL 2020, 2020 | 119* | 2020 |
| Self-Training with Weak Supervision G Karamanolakis, S Mukherjee, G Zheng, AH Awadallah NAACL 2021, 2021 | 114 | 2021 |
| Gender Bias in Multilingual Embeddings and Cross-Lingual Transfer J Zhao, S Mukherjee, S Hosseini, KW Chang, AH Awadallah ACL 2020, 2020 | 114 | 2020 |
| Leveraging Multi-Source Weak Social Supervision for Early Detection of Fake News K Shu, G Zheng, Y Li, S Mukherjee, AH Awadallah, S Ruston, H Liu ECML-PKDD 2020, 2020 | 113* | 2020 |
| Fairness via Representation Neutralization M Du, S Mukherjee, G Wang, R Tang, AH Awadallah, X Hu NeurIPS 2021, 2021 | 105 | 2021 |
Ahmed H. AwadallahMicrosoft ResearchVerified email at microsoft.com
