How do Large Language Models Learn In-Context? Query and Key Matrices of In-Context Heads are Two Towers for Metric Learning

How do Large Language Models Learn In-Context? Query and Key Matrices of In-Context Heads are Two Towers for Metric Learning Zeping Yu author Sophia Ananiadou author 2024-11 text Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing Yaser Al-Onaizan editor Mohit Bansal editor Yun-Nung Chen editor Association for Computational Linguistics Miami, Florida, USA conference publication yu-ananiadou-2024-large 10.18653/v1/2024.emnlp-main.192 https://aclanthology.org/2024.emnlp-main.192/ 2024-11 3281 3292