Lee, G., Lee, J., Hong, S., Kim, M., Ahn, E., Chang, D.-S. and Choi, J. 2025. RILQ: Rank-Insensitive LoRA-Based Quantization Error Compensation for Boosting 2-Bit Large Language Model Accuracy. Proceedings of the AAAI Conference on Artificial Intelligence. 39, 17 (Apr. 2025), 18091-18100. DOI:https://doi.org/10.1609/aaai.v39i17.33990.