| CrossFit: A Few-shot Learning Challenge for Cross-task Generalization in NLP Q Ye, BY Lin, X Ren EMNLP 2021, 2021 | 164 | 2021 |
| Prompt Engineering a Prompt Engineer Q Ye, M Axmed, R Pryzant, F Khani ACL 2024 (Findings), 2023 | 67* | 2023 |
| Learning from Explanations with Neural Execution Tree Z Wang, Y Qin, W Zhou, J Yan, Q Ye, L Neves, Z Liu, X Ren ICLR 2020, 2019 | 45* | 2019 |
| Refining language models with compositional explanations H Yao, Y Chen, Q Ye, X Jin, X Ren NeurIPS 2021, 2021 | 44* | 2021 |
| Learning to Generate Task-Specific Adapters from Task Description Q Ye, X Ren ACL-IJCNLP 2021 (Short Paper), 2021 | 37* | 2021 |
| Teaching Machine Comprehension with Compositional Explanations Q Ye, X Huang, E Boschee, X Ren EMNLP 2020 (Findings), 2020 | 33 | 2020 |
| Semi-automated protocol disambiguation and code generation J Yen, T Lévai, Q Ye, X Ren, R Govindan, B Raghavan SIGCOMM 2021, 272-286, 2021 | 30 | 2021 |
| LEAN-LIFE: A Label-Efficient Annotation Framework Towards Learning from Explanation DH Lee, R Khanna, BY Lin, J Chen, S Lee, Q Ye, E Boschee, L Neves, ... ACL 2020 (Demo Track), 2020 | 21 | 2020 |
| Looking Beyond Label Noise: Shifted Label Distribution Matters in Distantly Supervised Relation Extraction Q Ye, L Liu, M Zhang, X Ren EMNLP-IJCNLP 2019, 2019 | 21 | 2019 |
| How Predictable Are Large Language Model Capabilities? A Case Study on BIG-bench Q Ye, HY Fu, X Ren, R Jia EMNLP 2023 (Findings), 2023 | 15 | 2023 |
| Eliciting and Understanding Cross-Task Skills with Task-Level Mixture-of-Experts Q Ye, J Zha, X Ren EMNLP 2022 (Findings), 2022 | 15* | 2022 |
| On the Influence of Masking Policies in Intermediate Pre-training Q Ye, BZ Li, S Wang, B Bolte, H Ma, W Yih, X Ren, M Khabsa EMNLP 2021, 2021 | 13 | 2021 |
| Studying strategically: Learning to mask for closed-book QA Q Ye, BZ Li, S Wang, B Bolte, H Ma, W Yih, X Ren, M Khabsa arXiv preprint arXiv:2012.15856, 2020 | 10 | 2020 |
| LLM-driven Instruction Following: Progresses and Concerns W Yin, Q Ye, P Liu, X Ren, H Schütze Proceedings of the 2023 Conference on Empirical Methods in Natural Language …, 2023 | 9 | 2023 |
| FiD-ICL: A Fusion-in-Decoder Approach for Efficient In-Context Learning Q Ye, I Beltagy, ME Peters, X Ren, H Hajishirzi ACL 2023, 2022 | 9 | 2022 |
| Estimating Large Language Model Capabilities without Labeled Test Data HY Fu, Q Ye, A Xu, X Ren, R Jia EMNLP 2023 (Findings), 2023 | 8 | 2023 |
| Stress-Testing Long-Context Language Models with Lifelong ICL and Task Haystack X Xu, Q Ye, X Ren NeurIPS 2024 (Datasets and Benchmarks Track), 2024 | 2 | 2024 |
| Sparse Distillation: Speeding Up Text Classification by Using Bigger Student Models Q Ye, M Khabsa, M Lewis, S Wang, X Ren, A Jaech NAACL 2022, 2021 | 2 | 2021 |
| Cross-Task Generalization Abilities of Large Language Models Q Ye Proceedings of the 2024 Conference of the North American Chapter of the …, 2024 | | 2024 |
Sean (Xiang) RenViterbi Early Career Chair & Associate Professor, University of Southern CaliforniaAdresse e-mail validée de usc.edu
