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

arXiv: https://arxiv.org/abs/2512.06744 · HTML: https://mlsanity.com/paper/2512.06744/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 32 references that are in the map.
- First posted on arXiv 7 Dec 2025.

## Builds on (most cited first, 16 of 16)

- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013)
- [A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference](https://mlsanity.com/paper/1704.05426/) (2017)
- [A large annotated corpus for learning natural language inference](https://mlsanity.com/paper/1508.05326/) (2015)
- [Enriching Word Vectors with Subword Information](https://mlsanity.com/paper/1607.04606/) (2016)
- [Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models](https://mlsanity.com/paper/2506.05176/) (2025)
- [ConceptNet 5.5: An Open Multilingual Graph of General Knowledge](https://mlsanity.com/paper/1612.03975/) (2016)
- [MPNet: Masked and Permuted Pre-training for Language Understanding](https://mlsanity.com/paper/2004.09297/) (2020)
- [How Contextual are Contextualized Word Representations? Comparing the Geometry of BERT, ELMo, and GPT-2 Embeddings](https://mlsanity.com/paper/1909.00512/) (2019)
- [One Embedder, Any Task: Instruction-Finetuned Text Embeddings](https://mlsanity.com/paper/2212.09741/) (2022)
- [SimLex-999: Evaluating Semantic Models with (Genuine) Similarity Estimation](https://mlsanity.com/paper/1408.3456/) (2014)
- [SimVerb-3500: A Large-Scale Evaluation Set of Verb Similarity](https://mlsanity.com/paper/1608.00869/) (2016)
- [HyperLex: A Large-Scale Evaluation of Graded Lexical Entailment](https://mlsanity.com/paper/1608.02117/) (2016)
- [Revisiting Word Embeddings in the LLM Era](https://mlsanity.com/paper/2402.11094/) (2024)
- [The Impact of Word Splitting on the Semantic Content of Contextualized Word Representations](https://mlsanity.com/paper/2402.14616/) (2024)
- [Matrix Factorization using Window Sampling and Negative Sampling for Improved Word Representations](https://mlsanity.com/paper/1606.00819/) (2016)

## Built on by (most cited first, 1 of 1)

- [Disentangling Similarity and Relatedness in Topic Models](https://mlsanity.com/paper/2603.10619/) (2026)

## Abstract (arXiv)

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 +0.29 on SimLex-999. Some models fail completely on bare words (correlation = 0) but recover with prompts (+0.73 improvement). Our best results achieve correlation = 0.692 on SimLex-999 with embed-english-v3.0 (Cohere), correlation = 0.811 on WordSim-353, and correlation = 0.855 on MEN-3000 with text-embedding-3-large (OpenAI). These results outperform classic static embeddings like Word2Vec (correlation = 0.40) and even the best static method LexVec (correlation = 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.