@inproceedings{558a28d737d6496fa75cb6cb3bd65a97,
title = "BeLLM: Backward Dependency Enhanced Large Language Model for Sentence Embeddings",
abstract = "Sentence embeddings are crucial in measuring semantic similarity. Most recent studies employed large language models (LLMs) to learn sentence embeddings. Existing LLMs mainly adopted autoregressive architecture without explicit backward dependency modeling. Therefore, we examined the effects of backward dependencies in LLMs for semantic similarity measurements. Concretely, we propose a novel model: backward dependency enhanced large language model (BeLLM). It learns sentence embeddings via transforming specific attention layers from uni- to bi-directional. We extensively experiment across various semantic textual similarity (STS) tasks and downstream applications. BeLLM achieves state-of-the-art performance in varying scenarios. It shows that autoregressive LLMs benefit from backward dependencies for sentence embeddings.",
author = "Xianming Li and Jing Li",
note = "Publisher Copyright: {\textcopyright} 2024 Association for Computational Linguistics.",
year = "2024",
month = jun,
language = "English",
series = "Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL 2024",
publisher = "Association for Computational Linguistics (ACL)",
pages = "792--804",
editor = "Kevin Duh and Helena Gomez and Steven Bethard",
booktitle = "Long Papers",
address = "United States",
}