Ailiang Lin, Zhuoyun Li, Yusong Wang 0003, Kotaro Funakoshi, Manabu Okumura. Causal2Vec: Improving Decoder-only LLMs as Embedding Models through a Contextual Token. In Maria Liakata, Viviane P. Moreira, Jiajun Zhang 0001, David Jurgens, editors, Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 2026, San Diego, California, United States, July 2-7, 2026. pages 22769-22788, Association for Computational Linguistics, 2026. [doi]
Abstract is missing.