<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ranjan-2026-one">
    <titleInfo>
        <title>One Word Is Not Enough: Simple Prompts Improve Word Embeddings</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Rajeev</namePart>
        <namePart type="family">Ranjan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 15th Joint Conference on Lexical and Computational Semantics (*SEM 2026)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Saif</namePart>
            <namePart type="given">M</namePart>
            <namePart type="family">Mohammad</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Nedjma</namePart>
            <namePart type="family">Ousidhoum</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">San Diego, California, United States</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-413-2</identifier>
    </relatedItem>
    <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 (\ensuremathρ \ensuremath\approx 0) but recover with prompts (+0.73 improvement). Our best results achieve \ensuremathρ=0.692 on SimLex-999 with embed-english-v3.0 (Cohere), \ensuremathρ=0.811 on WordSim-353, and \ensuremathρ=0.855 on MEN-3000 with text-embedding-3-large (OpenAI). These results outperform classic static embeddings like Word2Vec (\ensuremathρ=0.40) and even the best static method LexVec (\ensuremathρ=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.</abstract>
    <identifier type="citekey">ranjan-2026-one</identifier>
    <location>
        <url>https://aclanthology.org/2026.starsem-conference.32/</url>
    </location>
    <part>
        <date>2026-07</date>
        <extent unit="page">
            <start>464</start>
            <end>473</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T One Word Is Not Enough: Simple Prompts Improve Word Embeddings
%A Ranjan, Rajeev
%Y Mohammad, Saif M.
%Y Ousidhoum, Nedjma
%S Proceedings of the 15th Joint Conference on Lexical and Computational Semantics (*SEM 2026)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-413-2
%F ranjan-2026-one
%X 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 (\ensuremathρ \ensuremath\approx 0) but recover with prompts (+0.73 improvement). Our best results achieve \ensuremathρ=0.692 on SimLex-999 with embed-english-v3.0 (Cohere), \ensuremathρ=0.811 on WordSim-353, and \ensuremathρ=0.855 on MEN-3000 with text-embedding-3-large (OpenAI). These results outperform classic static embeddings like Word2Vec (\ensuremathρ=0.40) and even the best static method LexVec (\ensuremathρ=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.
%U https://aclanthology.org/2026.starsem-conference.32/
%P 464-473

Markdown (Informal)

[One Word Is Not Enough: Simple Prompts Improve Word Embeddings](https://aclanthology.org/2026.starsem-conference.32/) (Ranjan, *SEM 2026)

• One Word Is Not Enough: Simple Prompts Improve Word Embeddings (Ranjan, *SEM 2026)

ACL

• Rajeev Ranjan. 2026. One Word Is Not Enough: Simple Prompts Improve Word Embeddings. In Proceedings of the 15th Joint Conference on Lexical and Computational Semantics (*SEM 2026), pages 464–473, San Diego, California, United States. Association for Computational Linguistics.