| Vlind-bench: Measuring language priors in large vision-language models K Lee, M Kim, S Yoon, M Kim, D Lee, H Koh, K Jung Findings of the Association for Computational Linguistics: NAACL 2025, 4129-4144, 2025 | 24 | 2025 |
| Target-agnostic gender-aware contrastive learning for mitigating bias in multilingual machine translation M Lee, H Koh, K Lee, D Zhang, M Kim, K Jung arXiv preprint arXiv:2305.14016, 2023 | 13 | 2023 |
| Fine-grained gender control in machine translation with large language models M Lee, H Koh, M Kim, K Jung arXiv preprint arXiv:2407.15154, 2024 | 7 | 2024 |
| Generating diverse hypotheses for inductive reasoning K Lee, H Koh, D Lee, S Yoon, M Kim, K Jung Proceedings of the 2025 Conference of the Nations of the Americas Chapter of …, 2025 | 5 | 2025 |
| Faithun: Toward faithful forgetting in language models by investigating the interconnectedness of knowledge N Yang, M Kim, S Yoon, J Shin, K Jung arXiv preprint arXiv:2502.19207, 2025 | 5 | 2025 |
| Rethinking Post-Unlearning Behavior of Large Vision-Language Models M Kim, N Yang, K Jung arXiv preprint arXiv:2506.02541, 2025 | 2 | 2025 |
| Training Dynamics of Parametric and In-Context Knowledge Utilization in Language Models M Kim, DK Kim, J Kwon, N Yang, K Jung, M Cha arXiv preprint arXiv:2510.02370, 2025 | 1 | 2025 |
| Erase or Hide? Suppressing Spurious Unlearning Neurons for Robust Unlearning N Yang, DK Kim, J Kwon, M Kim, K Jung, M Cha arXiv preprint arXiv:2509.22263, 2025 | | 2025 |
| Bilinear relational structure fixes reversal curse and enables consistent model editing DK Kim, M Kim, J Kwon, N Yang, M Cha arXiv preprint arXiv:2509.21993, 2025 | | 2025 |
| A New Framework for Evaluating Faithfulness of Video Moment Retrieval against Multiple Distractors N Yang, M Kim, S Yoon, J Shin, K Jung Proceedings of the 33rd ACM International Conference on Information and …, 2024 | | 2024 |
| In Search of the Engram in LLMs: A Neuroscience Perspective on the Memory Functions in AI Models M Kim, J Kwon, DK Kim, M Cha The Fourth Blogpost Track at ICLR 2025, 0 | | |
