| Pandagpt: One model to instruction-follow them all Y Su, T Lan, H Li, J Xu, Y Wang, D Cai TLLM'23, 2023 | 278 | 2023 |
| A survey on retrieval-augmented text generation H Li, Y Su, D Cai, Y Wang, L Liu arXiv preprint arXiv:2202.01110, 2022 | 275* | 2022 |
| A Contrastive Framework for Neural Text Generation Y Su, T Lan, Y Wang, D Yogatama, L Kong, N Collier NeurIPS'22 (Spotlight), 2022 | 234* | 2022 |
| Multi-Task Pre-Training for Plug-and-Play Task-Oriented Dialogue System Y Su, L Shu, E Mansimov, A Gupta, D Cai, YA Lai, Y Zhang ACL'22, 2021 | 190 | 2021 |
| Starcoder 2 and the stack v2: The next generation A Lozhkov, R Li, LB Allal, F Cassano, J Lamy-Poirier, N Tazi, A Tang, ... arXiv preprint arXiv:2402.19173, 2024 | 188 | 2024 |
| Language models can see: plugging visual controls in text generation Y Su, T Lan, Y Liu, F Liu, D Yogatama, Y Wang, L Kong, N Collier arXiv preprint arXiv:2205.02655, 2022 | 116* | 2022 |
| Plan-then-Generate: Controlled Data-to-Text Generation via Planning Y Su, D Vandyke, S Wang, Y Fang, N Collier EMNLP'21-Findings, 2021 | 81 | 2021 |
| Replacing Judges with Juries: Evaluating LLM Generations with a Panel of Diverse Models P Verga, S Hofstatter, S Althammer, Y Su, A Piktus, A Arkhangorodsky, ... arXiv preprint arXiv:2404.18796, 2024 | 61* | 2024 |
| TaCL: Improving BERT Pre-training with Token-aware Contrastive Learning Y Su, F Liu, Z Meng, L Shu, E Shareghi, N Collier NAACL'22-Findings, 2021 | 59 | 2021 |
| Non-autoregressive text generation with pre-trained language models Y Su, D Cai, Y Wang, D Vandyke, S Baker, P Li, N Collier EACL'21, 2021 | 52 | 2021 |
| Contrastive search is what you need for neural text generation Y Su, N Collier TMLR'23, 2022 | 48 | 2022 |
| Dialogue Response Selection with Hierarchical Curriculum Learning Y Su, D Cai, Q Zhou, Z Lin, S Baker, Y Cao, S Shi, N Collier, Y Wang ACL'21, 2021 | 46 | 2021 |
| Rewire-then-Probe: A Contrastive Recipe for Probing Biomedical Knowledge of Pre-trained Language Models Z Meng, F Liu, E Shareghi, Y Su, C Collins, N Collier ACL'22, 2021 | 43* | 2021 |
| Prototype-to-style: Dialogue generation with style-aware editing on retrieval memory Y Su, Y Wang, D Cai, S Baker, A Korhonen, N Collier TASLP'21, 2021 | 37 | 2021 |
| Few-Shot Table-to-Text Generation with Prototype Memory Y Su, Z Meng, S Baker, N Collier EMNLP'21-Findings, 2021 | 33 | 2021 |
| Sparkles: Unlocking chats across multiple images for multimodal instruction-following models Y Huang, Z Meng, F Liu, Y Su, N Collier, Y Lu arXiv preprint arXiv:2308.16463, 2023 | 29* | 2023 |
| Keep the Primary, Rewrite the Secondary: A Two-Stage Approach for Paraphrase Generation Y Su, D Vandyke, S Baker, Y Wang, N Collier ACL'21-Findings, 2021 | 21 | 2021 |
| Specialist or Generalist? Instruction Tuning for Specific NLP Tasks C Shi, Y Su, C Yang, Y Yang, D Cai EMNLP'23, 2023 | 17* | 2023 |
| To code, or not to code? exploring impact of code in pre-training V Aryabumi, Y Su, R Ma, A Morisot, I Zhang, A Locatelli, M Fadaee, ... arXiv preprint arXiv:2408.10914, 2024 | 13* | 2024 |
| Exploring dense retrieval for dialogue response selection T Lan, D Cai, Y Wang, Y Su, H Huang, XL Mao ACM Transactions on Information Systems 42 (3), 1-29, 2024 | 13* | 2024 |
Nigel CollierProfessor of Natural Language Processing, University of CambridgeVerified email at cam.ac.uk