---
title: "One Word Is Not Enough: Simple Prompts Improve Word Embeddings — Ranjan 2026"
description: "The author compares eight input conditions across seven models: four whitespace variants and four short semantic templates, such as… 30 references."
authors: ["Rajeev Ranjan"]
year: 2026
venue: "Proceedings of the 15th Joint Conference on Lexical and Computational Semantics (*SEM 2026)"
source: "https://aclanthology.org/2026.starsem-conference.32/"
doi: "10.18653/v1/2026.starsem-conference.32"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/ranjan-2026-one-word-is-not-enough/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/ranjan-2026-one-word-is-not-enough/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/9/) / One Word Is Not Enough: Simple Prompts Improve Word Embeddings

# One Word Is Not Enough: Simple Prompts Improve Word Embeddings

**Authors:** Rajeev Ranjan · **Year:** 2026 · **Venue:** Proceedings of the 15th Joint Conference on Lexical and Computational Semantics (\*SEM 2026) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2026.starsem-conference.32/) · [PDF](https://aclanthology.org/2026.starsem-conference.32.pdf) · [DOI 10.18653/v1/2026.starsem-conference.32](https://doi.org/10.18653/v1/2026.starsem-conference.32) · [OpenAlex](https://openalex.org/W7166878658)

**Citations:** 0 citations (OpenAlex, 2026-10-14)

## Summary
Modern text embedding models are built and benchmarked for sentences, so their quality on single isolated words is poorly understood. This paper asks whether simple input formatting can improve word-level representations from such models without any training. The author compares eight input conditions across seven models: four whitespace variants and four short semantic templates, such as "meaning: w" or an instruction asking for the semantic concept. The models are OpenAI text-embedding-3-small/large, Cohere embed-english-v3.0, voyage-3, all-mpnet-base-v2, BGE-large-en-v1.5 and Qwen3-Embedding-8B. Evaluation uses Spearman correlation on SimLex-999, WordSim-353, MEN-3000 and SimVerb-3500, plus three downstream tasks: categorization, HyperLex entailment and WordNet synonym retrieval.

Semantic templates help every model, and they matter far more than whitespace tweaks. Some models that produce essentially random similarities on bare words become competitive once a prompt is added. The resulting scores surpass classic static embeddings and set a new best among methods that use no external knowledge. The technique is a free, zero-shot fix for anyone using sentence encoders for lexical semantics.

## Key points
- **Best results:** Cohere embed-english-v3.0 reaches ρ = 0.692 on SimLex-999. text-embedding-3-large reaches 0.811 on WordSim-353 and 0.855 on MEN-3000. The best static baseline on SimLex-999 is LexVec at about 0.48.
- **Bare-word failure in voyage-3:** voyage-3 scores near zero or negative on bare words, for example −0.07 on SimLex-999 and −0.022 on SimVerb-3500. With prompts it recovers strongly, rising from 0.096 to 0.826 on MEN-3000 (+0.73).
- **Gains for other models:** For models with reasonable baselines, SimLex-999 gains range from +0.04 to +0.28. Qwen3-Embedding-8B improves most (0.286 → 0.567), which shows that model size does not predict robustness.
- **Model-specific best prompt:** No single template wins everywhere. Instruction-style and "meaning:" prompts generally do best, and "word:" works best for BGE. Whitespace sensitivity follows the tokenizer: BPE-based models are affected, while WordPiece-based models are not.
- **Downstream and geometric effects:** Prompting improves BLESS purity, HyperLex and WordNet synonym MAP for nearly all models; voyage-3 gains +0.515 purity and +0.311 on HyperLex. Prompting also produces clearer category clusters in the embedding space. The study is limited to English.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

Fields: [Linguistics & languages](https://md.research.elamur.ai/free/en/shelves/linguistics/)

## Cite

Cite as: Rajeev Ranjan. 2026. One Word Is Not Enough: Simple Prompts Improve Word Embeddings. Proceedings of the 15th Joint Conference on Lexical and Computational Semantics (\*SEM 2026).

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{ranjan2026one,
  title = {{One Word Is Not Enough: Simple Prompts Improve Word Embeddings}},
  author = {Rajeev Ranjan},
  booktitle = {Proceedings of the 15th Joint Conference on Lexical and Computational Semantics (*SEM 2026)},
  year = {2026},
  doi = {10.18653/v1/2026.starsem-conference.32},
  url = {https://doi.org/10.18653/v1/2026.starsem-conference.32}
}
```

- [← previous One Size Does Not Fit All: Why EU Legislative Translation Demands Domain-Specific Fine-Tuning of LLMs](https://md.research.elamur.ai/free/en/papers/lorini-2026-one-size-does-not-fit/)
- [next → Onomasiological Sense Alignment Across Dialect Dictionaries. A Taxonomy-Constrained LLM Classification](https://md.research.elamur.ai/free/en/papers/mederake-2026-onomasiological-sense-alignment-across-dialect/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/9/)

## References

30 references, 15 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Abdulrahman Almuhareb and Massimo Poesio. 2004. Attribute-based and value-based clustering: An evaluation. In Proceedings of the 2004 Conference on Empirical Methods in Natural Language Processing, pages 158–165. [find](https://scholar.google.com/scholar?q=Abdulrahman+Almuhareb+and+Massimo+Poesio%2E+2004%2E+Attribute%2Dbased+and+value%2Dbased+clustering%3A+An+evaluation%2E+In+Proceedings+of+the+2004+Conference+on+Empirical+Methods+in+Natural+Language+Processing%2C+pa)
2. Marco Baroni and Alessandro Lenci. 2011. How we BLESSed distributional semantic evaluation. In Proceedings of the GEMS 2011 Workshop on GEometrical Models of Natural Language Semantics, pages 1–10. [our card](https://md.research.elamur.ai/free/en/papers/baroni-2011-how-we-blessed-distributional-semantic/)
3. William F. Battig and William E. Montague. 1969. Category norms of verbal items in 56 categories: A replication and extension of the Connecticut category norms. Journal of Experimental Psychology, 80(3p2):1. [find](https://scholar.google.com/scholar?q=William+F%2E+Battig+and+William+E%2E+Montague%2E+1969%2E+Category+norms+of+verbal+items+in+56+categories%3A+A+replication+and+extension+of+the+Connecticut+category+norms%2E+Journal+of+Experimental+Psychology%2C+80%28)
4. Piotr Bojanowski, Edouard Grave, Armand Joulin, and Tomas Mikolov. 2017. Enriching word vectors with subword information. Transactions of the Association for Computational Linguistics, 5:135–146. [our card](https://md.research.elamur.ai/free/en/papers/bojanowski-2017-enriching-word-vectors-subword-information/)
5. Rishi Bommasani, Kelly Davis, and Claire Cardie. 2020. Interpreting pretrained contextualized representations via reductions to static embeddings. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 4758– 4781, Online. Association for Computational Lingu… [our card](https://md.research.elamur.ai/free/en/papers/bommasani-2020-interpreting-pretrained-contextualized-representations-reductions/)
6. Samuel R. Bowman, Gabor Angeli, Christopher Potts, and Christopher D. Manning. 2015. A large annotated corpus for learning natural language inference. In Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, pages 632–642, Lisbon, Portugal. Association for Computati… [find](https://scholar.google.com/scholar?q=Samuel+R%2E+Bowman%2C+Gabor+Angeli%2C+Christopher+Potts%2C+and+Christopher+D%2E+Manning%2E+2015%2E+A+large+annotated+corpus+for+learning+natural+language+inference%2E+In+Proceedings+of+the+2015+Conference+on+Empirica)
7. Hong Kong, China. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Hong+Kong%2C+China%2E+Association+for+Computational+Linguistics%2E)
8. Lev Finkelstein, Evgeniy Gabrilovich, Yossi Matias, Ehud Rivlin, Zach Solan, Gadi Wolfman, and Eytan Ruppin. 2002. Placing search in context: The concept revisited. ACM Transactions on Information Systems, 20(1):116–131. [find](https://scholar.google.com/scholar?q=Lev+Finkelstein%2C+Evgeniy+Gabrilovich%2C+Yossi+Matias%2C+Ehud+Rivlin%2C+Zach+Solan%2C+Gadi+Wolfman%2C+and+Eytan+Ruppin%2E+2002%2E+Placing+search+in+context%3A+The+concept+revisited%2E+ACM+Transactions+on+Information+Sys)
9. Aina Garı́ Soler, Matthieu Labeau, and Chloé Clavel. 2024. The impact of word splitting on the semantic content of contextualized word representations. Transactions of the Association for Computational Linguistics, 12:299–320. [find](https://scholar.google.com/scholar?q=Aina+Gar%C4%B1%CC%81+Soler%2C+Matthieu+Labeau%2C+and+Chloe%CC%81+Clavel%2E+2024%2E+The+impact+of+word+splitting+on+the+semantic+content+of+contextualized+word+representations%2E+Transactions+of+the+Association+for+Computation)
10. Daniela Gerz, Ivan Vulić, Felix Hill, Roi Reichart, and Anna Korhonen. 2016. SimVerb-3500: A large-scale evaluation set of verb similarity. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pages 2173–2182, Austin, Texas. Association for Computational Lingui… [our card](https://md.research.elamur.ai/free/en/papers/gerz-2016-simverb-3500-large-scale-evaluation/)
11. Felix Hill, Roi Reichart, and Anna Korhonen. 2015. SimLex-999: Evaluating semantic models with (genuine) similarity estimation. Computational Linguistics, 41(4):665–695. [our card](https://md.research.elamur.ai/free/en/papers/hill-2015-simlex-999-evaluating-semantic-models/)
12. Ting Jiang, Shaohan Huang, Zhongzhi Luan, Deqing Wang, and Fuzhen Zhuang. 2024. Scaling sentence embeddings with large language models. In Findings of the Association for Computational Linguistics: EMNLP 2024. [find](https://scholar.google.com/scholar?q=Ting+Jiang%2C+Shaohan+Huang%2C+Zhongzhi+Luan%2C+Deqing+Wang%2C+and+Fuzhen+Zhuang%2E+2024%2E+Scaling+sentence+embeddings+with+large+language+models%2E+In+Findings+of+the+Association+for+Computational+Linguistics%3A+EM)
13. Yibin Lei, Di Wu, Tianyi Zhou, Tao Shen, Yu Cao, Chongyang Tao, and Andrew Yates. 2024. Meta-task prompting elicits embeddings from large language models. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). [find](https://scholar.google.com/scholar?q=Yibin+Lei%2C+Di+Wu%2C+Tianyi+Zhou%2C+Tao+Shen%2C+Yu+Cao%2C+Chongyang+Tao%2C+and+Andrew+Yates%2E+2024%2E+Meta%2Dtask+prompting+elicits+embeddings+from+large+language+models%2E+In+Proceedings+of+the+62nd+Annual+Meeting+of+)
14. Tomas Mikolov, Kai Chen, Greg Corrado, and Jeffrey Dean. 2013. Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781. [our card](https://md.research.elamur.ai/free/en/papers/mikolov-2013-efficient-estimation-word-representations-vector/)
15. Elia Bruni, Gemma Boleda, Marco Baroni, and Nam-Khanh Tran. 2012. Distributional semantics in technicolor. In Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 136–145, Jeju Island, Korea. Association for Computational Linguistics. [our card](https://md.research.elamur.ai/free/en/papers/bruni-2012-distributional-semantics-technicolor/)
16. George A. Miller. 1995. WordNet: a lexical database for English. Communications of the ACM, 38(11):39–41. [our card](https://md.research.elamur.ai/free/en/papers/miller-1994-wordnet/)
17. Cohere. 2024. Embed - Cohere documentation. [https://docs.cohere.com/docs/](https://docs.cohere.com/docs/) cohere-embed. [↗](https://docs.cohere.com/docs/)
18. Jeffrey Pennington, Richard Socher, and Christopher Manning. 2014. GloVe: Global vectors for word representation. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 1532–1543, Doha, Qatar. Association for Computational Linguistics. [our card](https://md.research.elamur.ai/free/en/papers/pennington-2014-glove-global-vectors-word-representation/)
19. Kawin Ethayarajh. 2019. How contextual are contextualized word representations? Comparing the geometry of BERT, ELMo, and GPT-2 embeddings. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Process… [find](https://scholar.google.com/scholar?q=Kawin+Ethayarajh%2E+2019%2E+How+contextual+are+contextualized+word+representations%3F+Comparing+the+geometry+of+BERT%2C+ELMo%2C+and+GPT%2D2+embeddings%2E+In+Proceedings+of+the+2019+Conference+on+Empirical+Methods+i)
20. Qwen Team. 2025. Qwen3 embedding: Advancing text embedding and reranking through foundation models. https://arxiv.org/abs/2506. 05176. [↗](https://arxiv.org/abs/2506) [our card](https://md.research.elamur.ai/free/en/papers/zhang-2025-qwen3-embedding-advancing-text/)
21. Nils Reimers and Iryna Gurevych. 2019. Sentence-BERT: Sentence embeddings using Siamese BERT-networks. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 3982–3992,… [our card](https://md.research.elamur.ai/free/en/papers/reimers-2019-sentence-bert-sentence-embeddings-siamese/)
22. Alexandre Salle, Aline Villavicencio, and Marco Idiart. 2016. Matrix factorization using window sampling and negative sampling for improved word representations. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 419–424, Berlin… [find](https://scholar.google.com/scholar?q=Alexandre+Salle%2C+Aline+Villavicencio%2C+and+Marco+Idiart%2E+2016%2E+Matrix+factorization+using+window+sampling+and+negative+sampling+for+improved+word+representations%2E+In+Proceedings+of+the+54th+Annual+Meet)
23. Kaitao Song, Xu Tan, Tao Qin, Jianfeng Lu, and Tie-Yan Liu. 2020. MPNet: Masked and permuted pre-training for language understanding. Preprint, arXiv:2004.09297. [our card](https://md.research.elamur.ai/free/en/papers/song-2020-mpnet-masked-permuted-pre-training/)
24. Robyn Speer, Joshua Chin, and Catherine Havasi. 2017. ConceptNet 5.5: An open multilingual graph of general knowledge. In Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence, pages 4444–4451. [find](https://scholar.google.com/scholar?q=Robyn+Speer%2C+Joshua+Chin%2C+and+Catherine+Havasi%2E+2017%2E+ConceptNet+5%2E5%3A+An+open+multilingual+graph+of+general+knowledge%2E+In+Proceedings+of+the+Thirty%2DFirst+AAAI+Conference+on+Artificial+Intelligence%2C+pa)
25. Hongjin Su, Weijia Shi, Jungo Kasai, Yizhong Wang, Yushi Hu, Mari Ostendorf, Wen-tau Yih, Noah A. Smith, Luke Zettlemoyer, and Tao Yu. 2023. One embedder, any task: Instruction-finetuned text embeddings. In Findings of the Association for Computational Linguistics: ACL 2023, pages 1102– 1121, Toront… [our card](https://md.research.elamur.ai/free/en/papers/su-2022-one-embedder-any-task-instruction/)
26. Voyage AI. 2024. Text embeddings - Voyage AI documentation. [https://docs.voyageai.com/](https://docs.voyageai.com/) docs/embeddings. [↗](https://docs.voyageai.com/)
27. Ivan Vulić, Daniela Gerz, Douwe Kiela, Felix Hill, and Anna Korhonen. 2017. HyperLex: A large-scale evaluation of graded lexical entailment. Computational Linguistics, 43(4):781–835. [find](https://scholar.google.com/scholar?q=Ivan+Vulic%CC%81%2C+Daniela+Gerz%2C+Douwe+Kiela%2C+Felix+Hill%2C+and+Anna+Korhonen%2E+2017%2E+HyperLex%3A+A+large%2Dscale+evaluation+of+graded+lexical+entailment%2E+Computational+Linguistics%2C+43%284%29%3A781%E2%80%93835%2E)
28. Liang Wang, Nan Yang, Xiaolong Huang, Linjun Yang, Rangan Majumder, and Furu Wei. 2024. Improving text embeddings with large language models. arXiv preprint arXiv:2401.00368. [our card](https://md.research.elamur.ai/free/en/papers/wang-2024-improving-text-embeddings-large-language/)
29. Adina Williams, Nikita Nangia, and Samuel Bowman. 2018. A broad-coverage challenge corpus for sentence understanding through inference. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Pa… [find](https://scholar.google.com/scholar?q=Adina+Williams%2C+Nikita+Nangia%2C+and+Samuel+Bowman%2E+2018%2E+A+broad%2Dcoverage+challenge+corpus+for+sentence+understanding+through+inference%2E+In+Proceedings+of+the+2018+Conference+of+the+North+American+Chap)
30. Shitao Xiao, Zheng Liu, Peitian Zhang, Niklas Muennighoff, Defu Lian, and Jian-Yun Nie. 2023. C-pack: Packed resources for general chinese embeddings. arXiv preprint arXiv:2309.07597. [our card](https://md.research.elamur.ai/free/en/papers/xiao-2023-c-pack-packed-resources/)