| Large language models are few-shot clinical information extractors M Agrawal, S Hegselmann, H Lang, Y Kim, D Sontag EMNLP 2022, 2022 | 621 | 2022 |
| TabLLM: Few-shot classification of tabular data with large language models S Hegselmann, A Buendia, H Lang, M Agrawal, X Jiang, D Sontag International Conference on Artificial Intelligence and Statistics, 5549-5581, 2023 | 538 | 2023 |
| Understanding the role of momentum in stochastic gradient methods I Gitman, H Lang, P Zhang, L Xiao Advances in Neural Information Processing Systems, 9630-9640, 2019 | 139 | 2019 |
| Who should predict? exact algorithms for learning to defer to humans H Mozannar, H Lang, D Wei, P Sattigeri, S Das, D Sontag International conference on artificial intelligence and statistics, 10520-10545, 2023 | 94 | 2023 |
| Co-training improves prompt-based learning for large language models H Lang, MN Agrawal, Y Kim, D Sontag International Conference on Machine Learning, 11985-12003, 2022 | 70 | 2022 |
| Learning to Decode Collaboratively with Multiple Language Models SZ Shen, H Lang, B Wang, Y Kim, D Sontag ACL 2024, 2024 | 59 | 2024 |
| Theoretical analysis of weak-to-strong generalization H Lang, D Sontag, A Vijayaraghavan Advances in Neural Information Processing Systems 37, 46837-46880, 2024 | 45* | 2024 |
| Using statistics to automate stochastic optimization H Lang, P Zhang, L Xiao Advances in Neural Information Processing Systems, 9540-9550, 2019 | 32 | 2019 |
| Training Subset Selection for Weak Supervision H Lang, A Vijayaraghavan, D Sontag Advances in Neural Information Processing Systems 35, 16023-16036, 2022 | 27 | 2022 |
| When one llm drools, multi-llm collaboration rules S Feng, W Ding, A Liu, Z Wang, W Shi, Y Wang, Z Shen, X Han, H Lang, ... arXiv preprint arXiv:2502.04506, 2025 | 26 | 2025 |
| Self-supervised self-supervision by combining deep learning and probabilistic logic H Lang, H Poon Proceedings of the AAAI Conference on Artificial Intelligence 35 (6), 4978, 2021 | 17 | 2021 |
| Leveraging time irreversibility with order-contrastive pre-training MN Agrawal*, H Lang*, M Offin, L Gazit, D Sontag International Conference on Artificial Intelligence and Statistics, 2330-2353, 2022 | 16 | 2022 |
| Optimality of approximate inference algorithms on stable instances H Lang, D Sontag, A Vijayaraghavan International Conference on Artificial Intelligence and Statistics, 1157-1166, 2018 | 12* | 2018 |
| Statistical adaptive stochastic gradient methods P Zhang, H Lang, Q Liu, L Xiao arXiv preprint arXiv:2002.10597, 2020 | 10 | 2020 |
| Prefpalette: Personalized preference modeling with latent attributes SS Li, M Sclar, H Lang, A Ni, J He, P Xu, A Cohen, CY Park, Y Tsvetkov, ... arXiv preprint arXiv:2507.13541, 2025 | 6 | 2025 |
| Block stability for MAP inference H Lang, D Sontag, A Vijayaraghavan The 22nd International Conference on Artificial Intelligence and Statistics …, 2019 | 6 | 2019 |
| Beyond perturbation stability: LP recovery guarantees for map inference on noisy stable instances H Lang*, A Reddy*, D Sontag, A Vijayaraghavan International Conference on Artificial Intelligence and Statistics, 3043-3051, 2021 | 4 | 2021 |
| Combining Probabilistic Logic and Deep Learning for Self-Supervised Learning P Hitzler, MK Sarker Neuro-Symbolic Artificial Intelligence: The State of the Art 342, 311, 2022 | 3 | 2022 |
| Graph cuts always find a global optimum for Potts models (with a catch) H Lang, D Sontag, A Vijayaraghavan International Conference on Machine Learning, 5990-5999, 2021 | 2 | 2021 |
| Rubric-Based Benchmarking and Reinforcement Learning for Advancing LLM Instruction Following Y He, W Li, H Zhang, S Li, K Mandyam, S Khosla, Y Xiong, N Wang, ... arXiv e-prints, arXiv: 2511.10507, 2025 | 1 | 2025 |
David SontagProfessor, Massachusetts Institute of TechnologyVerified email at csail.mit.edu
