Token Prepending: A Training-Free Approach for Eliciting Better Sentence Embeddings from LLMs
Yuchen Fu, Zifeng Cheng, Zhiwei Jiang, Zhonghui Wang, Yafeng Yin, Zhengliang Li, Qing Gu. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.
Authors
- Zhengliang Li (ORCID: https://orcid.org/0000-0003-3021-2453)
- Zifeng Cheng (ORCID: https://orcid.org/0000-0002-8486-2614)
- Qing Gu (ORCID: https://orcid.org/0000-0002-5948-4690)
- Yuchen Fu
- Zhiwei Jiang (ORCID: https://orcid.org/0000-0001-5243-4992)
- Yafeng Yin (ORCID: https://orcid.org/0000-0002-9497-6244)
- Zhonghui Wang (ORCID: https://orcid.org/0000-0001-8930-645X)
Institutions
- Nanjing University (CN)
Publication Details
- Published
- 2025-01-01
- DOI
- https://doi.org/10.18653/v1/2025.acl-long.159
- Primary Topic
- Law, AI, and Intellectual Property
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- National Natural Science Foundation of China
- Fundamental Research Funds for the Central Universities