@inproceedings{ranjan-2026-one,
    title = "One Word Is Not Enough: Simple Prompts Improve Word Embeddings",
    author = "Ranjan, Rajeev",
    editor = "Mohammad, Saif M.  and
      Ousidhoum, Nedjma",
    booktitle = "Proceedings of the 15th Joint Conference on Lexical and Computational Semantics (*{SEM} 2026)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.starsem-conference.32/",
    pages = "464--473",
    ISBN = "979-8-89176-413-2",
    abstract = "Text embedding models are designed for sentence-level applications like retrieval and semantic similarity, and are primarily evaluated on sentence-level benchmarks. Their behavior on isolated words is less understood. We show that simply prepending semantic prompts to words before embedding substantially improves word similarity correlations. Testing 7 text embedding models, including text-embedding-3-large (OpenAI), embed-english-v3.0 (Cohere), voyage-3 (Voyage AI), all-mpnet-base-v2, and Qwen3-Embedding-8B, on 3 standard benchmarks (SimLex-999, WordSim-353, MEN-3000), we find that prompts like ``meaning: {word}'' or ``Represent the semantic concept: {word}'' improve Spearman correlations by up to +0.28 on SimLex-999. Some models fail completely on bare words ({\ensuremath{\rho}} {\ensuremath{\approx}} 0) but recover with prompts (+0.73 improvement). Our best results achieve {\ensuremath{\rho}}=0.692 on SimLex-999 with embed-english-v3.0 (Cohere), {\ensuremath{\rho}}=0.811 on WordSim-353, and {\ensuremath{\rho}}=0.855 on MEN-3000 with text-embedding-3-large (OpenAI). These results outperform classic static embeddings like Word2Vec ({\ensuremath{\rho}}=0.40) and even the best static method LexVec ({\ensuremath{\rho}}=0.48) on SimLex-999, establishing a new state-of-the-art for pure embedding methods. This zero-shot technique requires no training and works with any text embedding model."
}