Paraphrasing evades detectors of ai-generated text, but retrieval is an effective defense K Krishna, Y Song, M Karpinska, J Wieting, M Iyyer Advances in Neural Information Processing Systems 36, 2024 | 120 | 2024 |
A Critical Evaluation of Evaluations for Long-form Question Answering F Xu*, Y Song*, M Iyyer, E Choi ACL 2023, 2023 | 29 | 2023 |
DEMETR: Diagnosing Evaluation Metrics for Translation M Karpinska, N Raj, K Thai, Y Song, A Gupta, M Iyyer EMNLP 2022, 2022 | 22 | 2022 |
Knn-lm does not improve open-ended text generation S Wang, Y Song, A Drozdov, A Garimella, V Manjunatha, M Iyyer arXiv preprint arXiv:2305.14625, 2023 | 7 | 2023 |
SLING: Sino Linguistic Evaluation of Large Language Models Y Song, K Krishna, R Bhatt, M Iyyer EMNLP 2022, 2022 | 5 | 2022 |
Gee! grammar error explanation with large language models Y Song, K Krishna, R Bhatt, K Gimpel, M Iyyer arXiv preprint arXiv:2311.09517, 2023 | 3 | 2023 |
A comparative study of German and Chinese alternative questions Y Song Poster presented at the MiQ Workshop at the University of Konstanz, 2018 | 2 | 2018 |
Mandarin Chinese alternative questions are not disjoined polar questions Y Song | | |