| REPLUG: Retrieval-augmented black-box language models W Shi, S Min, M Yasunaga, M Seo, R James, M Lewis, L Zettlemoyer, ... NAACL 2024, 2023 | 532* | 2023 |
| Fine-grained human feedback gives better rewards for language model training Z Wu, Y Hu, W Shi, N Dziri, A Suhr, P Ammanabrolu, NA Smith, ... NeurIPS 2023 (Spotlight), 2024 | 285* | 2024 |
| One embedder, any task: Instruction-finetuned text embeddings H *Su, W *Shi, J Kasai, Y Wang, Y Hu, M Ostendorf, W Yih, NA Smith, ... ACL 2023, 2022 | 264 | 2022 |
| Selective annotation makes language models better few-shot learners H Su, J Kasai, CH Wu, W Shi, T Wang, J Xin, R Zhang, M Ostendorf, ... ICLR 2023, 2022 | 244* | 2022 |
| Detecting pretraining data from large language models W Shi, A Ajith, M Xia, Y Huang, D Liu, T Blevins, D Chen, L Zettlemoyer ICLR 2024, 2023 | 243 | 2023 |
| Embedding uncertain knowledge graphs X Chen, M Chen, W Shi, Y Sun, C Zaniolo AAAI 2019, 2019 | 161 | 2019 |
| RECOMP: Improving retrieval-augmented LMs with context compression and selective augmentation F Xu, W Shi, E Choi ICLR 2024, 2024 | 155* | 2024 |
| Trusting your evidence: Hallucinate less with context-aware decoding W Shi, X Han, M Lewis, Y Tsvetkov, L Zettlemoyer, SW Yih NAACL 2024, 2023 | 149 | 2023 |
| Promptcap: Prompt-guided task-aware image captioning Y Hu, H Hua, Z Yang, W Shi, NA Smith, J Luo ICCV 2023, 2022 | 148* | 2022 |
| Examining gender bias in languages with grammatical gender P Zhou, W Shi, J Zhao, KH Huang, M Chen, R Cotterell, KW Chang EMNLP 2019, 2019 | 147* | 2019 |
| Retrieval-augmented multimodal language modeling M Yasunaga, A Aghajanyan, W Shi, R James, J Leskovec, P Liang, ... ICML 2023, 2022 | 138 | 2022 |
| Ra-dit: Retrieval-augmented dual instruction tuning XV Lin, X Chen, M Chen, W Shi, M Lomeli, R James, P Rodriguez, J Kahn, ... ICLR 2024, 2023 | 117 | 2023 |
| Do membership inference attacks work on large language models? M Duan, A Suri, N Mireshghallah, S Min, W Shi, L Zettlemoyer, Y Tsvetkov, ... COLM 2024, 2024 | 108* | 2024 |
| On tractable representations of binary neural networks W Shi, A Shih, A Darwiche, A Choi KR 2020, 2020 | 97* | 2020 |
| Retrofitting contextualized word embeddings with paraphrases W Shi, M Chen, P Zhou, KW Chang EMNLP 2019, 2019 | 75* | 2019 |
| Knowledge Card: Filling LLMs' Knowledge Gaps with Plug-in Specialized Language Models S Feng, W Shi, Y Bai, V Balachandran, T He, Y Tsvetkov ICLR 2024 (Oral), 2023 | 73* | 2023 |
| Nonparametric masked language modeling S Min, W Shi, M Lewis, X Chen, W Yih, H Hajishirzi, L Zettlemoyer ACL 2023, 2022 | 69 | 2022 |
| Silo language models: Isolating legal risk in a nonparametric datastore S Min, S Gururangan, E Wallace, W Shi, H Hajishirzi, NA Smith, ... ICLR 2024 (Spotlight), 2023 | 64 | 2023 |
| Scaling expert language models with unsupervised domain discovery S Gururangan, M Li, M Lewis, W Shi, T Althoff, NA Smith, L Zettlemoyer arXiv preprint arXiv:2303.14177, 2023 | 63* | 2023 |
| Don't Hallucinate, Abstain: Identifying LLM Knowledge Gaps via Multi-LLM Collaboration S Feng, W Shi, Y Wang, W Ding, V Balachandran, Y Tsvetkov ACL 2024, Area Chair Award (QA track) 🏆 & Outstanding Paper Award 🏆, 2024 | 62 | 2024 |
Luke ZettlemoyerUniversity of Washington; MetaPatvirtintas el. paštas cs.washington.edu