Have you seen that number? investigating extrapolation in question answering models J Kim, G Hong, K Kim, J Kang, SH Myaeng Proceedings of the 2021 Conference on Empirical Methods in Natural Language …, 2021 | 17 | 2021 |
Ultra-high dimensional sparse representations with binarization for efficient text retrieval KR Jang, J Kang, G Hong, SH Myaeng, J Park, T Yoon, H Seo arXiv preprint arXiv:2104.07198, 2021 | 15 | 2021 |
Handling anomalies of synthetic questions in unsupervised question answering G Hong, J Kang, D Lim, SH Myaeng Proceedings of the 28th International Conference on Computational …, 2020 | 8 | 2020 |
UHD-BERT: Bucketed ultra-high dimensional sparse representations for full ranking KR Jang, J Kang, G Hong, SH Myaeng, J Park, T Yoon, H Seo CoRR, abs/2104.07198, 2021 | 7 | 2021 |
Aligning open ie relations and kb relations using a siamese network based on word embedding RA Putri, G Hong, SH Myaeng Proceedings of the 13th International Conference on Computational Semantics …, 2019 | 7 | 2019 |
Exploiting numerical-contextual knowledge to improve numerical reasoning in question answering J Kim, J Kang, K Kim, G Hong, SH Myaeng Findings of the Association for Computational Linguistics: NAACL 2022, 1811-1821, 2022 | 4 | 2022 |
Regularization of Distinct Strategies for Unsupervised Question Generation J Kang, G Hong, HP San Roman, SH Myaeng Findings of the Association for Computational Linguistics: EMNLP 2020, 3266-3277, 2020 | 4 | 2020 |
Discern and answer: Mitigating the impact of misinformation in retrieval-augmented models with discriminators G Hong, J Kim, J Kang, SH Myaeng, JJ Whang arXiv preprint arXiv:2305.01579, 2023 | 2 | 2023 |
Graph-induced transformers for efficient multi-hop question answering G Hong, J Kim, J Kang, SH Myaeng Proceedings of the 2022 Conference on Empirical Methods in Natural Language …, 2022 | 2 | 2022 |
Edinburgh Clinical NLP at SemEval-2024 Task 2: Fine-tune your model unless you have access to GPT-4 AP Gema, G Hong, P Minervini, L Daines, B Alex arXiv preprint arXiv:2404.00484, 2024 | 1 | 2024 |
FinePrompt: Unveiling the Role of Finetuned Inductive Bias on Compositional Reasoning in GPT-4 J Kim, G Hong, SH Myaeng, J Whang Findings of the Association for Computational Linguistics: EMNLP 2023, 3763-3775, 2023 | 1 | 2023 |
The Hallucinations Leaderboard--An Open Effort to Measure Hallucinations in Large Language Models G Hong, AP Gema, R Saxena, X Du, P Nie, Y Zhao, L Perez-Beltrachini, ... arXiv preprint arXiv:2404.05904, 2024 | | 2024 |
Edinburgh Clinical NLP at SemEval-2024 Task 2: Fine-tune your model unless you have access to GPT-4 A Pradipta Gema, G Hong, P Minervini, L Daines, B Alex arXiv e-prints, arXiv: 2404.00484, 2024 | | 2024 |
Why So Gullible? Enhancing the Robustness of Retrieval-Augmented Models against Counterfactual Noise G Hong, J Kim, J Kang, SH Myaeng, JJ Whang | | |