# Token Prepending: A Training-Free Approach for Eliciting Better Sentence Embeddings from LLMs

arXiv: https://arxiv.org/abs/2412.11556 · HTML: https://mlsanity.com/paper/2412.11556/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 40 references that are in the map.
- First posted on arXiv 16 Dec 2024.

## Builds on (most cited first, 20 of 20)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [SimCSE: Simple Contrastive Learning of Sentence Embeddings](https://mlsanity.com/paper/2104.08821/) (2021)
- [Qwen2 Technical Report](https://mlsanity.com/paper/2407.10671/) (2024)
- [Gemma 2: Improving Open Language Models at a Practical Size](https://mlsanity.com/paper/2408.00118/) (2024)
- [SemEval-2017 Task 1: Semantic Textual Similarity - Multilingual and Cross-lingual Focused Evaluation](https://mlsanity.com/paper/1708.00055/) (2017)
- [How Contextual are Contextualized Word Representations? Comparing the Geometry of BERT, ELMo, and GPT-2 Embeddings](https://mlsanity.com/paper/1909.00512/) (2019)
- [NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Models](https://mlsanity.com/paper/2405.17428/) (2024)
- [Sentence-T5: Scalable Sentence Encoders from Pre-trained Text-to-Text Models](https://mlsanity.com/paper/2108.08877/) (2021)
- [LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders](https://mlsanity.com/paper/2404.05961/) (2024)
- [One Embedder, Any Task: Instruction-Finetuned Text Embeddings](https://mlsanity.com/paper/2212.09741/) (2022)
- [Generative Representational Instruction Tuning](https://mlsanity.com/paper/2402.09906/) (2024)
- [Fantastic Semantics and Where to Find Them: Investigating Which Layers of Generative LLMs Reflect Lexical Semantics](https://mlsanity.com/paper/2403.01509/) (2024)
- [BeLLM: Backward Dependency Enhanced Large Language Model for Sentence Embeddings](https://mlsanity.com/paper/2311.05296/) (2023)
- [Simple Techniques for Enhancing Sentence Embeddings in Generative Language Models](https://mlsanity.com/paper/2404.03921/) (2024)
- [Meaning Representations from Trajectories in Autoregressive Models](https://mlsanity.com/paper/2310.18348/) (2023)
- [Composition-contrastive Learning for Sentence Embeddings](https://mlsanity.com/paper/2307.07380/) (2023)

## Built on by (most cited first, 18 of 18)

- [LLMs are Also Effective Embedding Models: An In-depth Overview](https://mlsanity.com/paper/2412.12591/) (2024)
- [Contrastive Prompting Enhances Sentence Embeddings in LLMs through Inference-Time Steering](https://mlsanity.com/paper/2505.12831/) (2025)
- [Position: Text Embeddings Should Capture Implicit Semantics, Not Just Surface Meaning](https://mlsanity.com/paper/2506.08354/) (2025)
- [FreeRet: MLLMs as Training-Free Retrievers](https://mlsanity.com/paper/2509.24621/) (2025)
- [RegionMarker: A Region-Triggered Semantic Watermarking Framework for Embedding-as-a-Service Copyright Protection](https://mlsanity.com/paper/2511.13329/) (2025)
- [Hierarchical Token Prepending: Enhancing Information Flow in Decoder-based LLM Embeddings](https://mlsanity.com/paper/2511.14868/) (2025)
- [Sparse Growing Transformer: Training-Time Sparse Depth Allocation via Progressive Attention Looping](https://mlsanity.com/paper/2603.23998/) (2026)
- [The Truth Lies Somewhere in the Middle (of the Generated Tokens)](https://mlsanity.com/paper/2605.09969/) (2026)
- [SemPA: Improving Sentence Embeddings of Large Language Models through Semantic Preference Alignment](https://mlsanity.com/paper/2601.05075/) (2026)
- [Focusing Condition: Inference-Time Self-Contrastive Steering Elicits Better Conditional Text Embeddings in LLMs](https://mlsanity.com/paper/2609.32684/) (2026)
- [Causal2Vec: Improving Decoder-only LLMs as Embedding Models through a Contextual Token](https://mlsanity.com/paper/2507.23386/) (2025)
- [KV-Embedding: Training-free Text Embedding via Internal KV Re-routing in Decoder-only LLMs](https://mlsanity.com/paper/2601.01046/) (2026)
- [Sequence Repetition Enhances Token Embeddings and Improves Sequence Labeling with Decoder-only Language Models](https://mlsanity.com/paper/2601.17585/) (2026)
- [Geometry-Aware Localized Watermarking for Copyright Protection in Embedding-as-a-Service](https://mlsanity.com/paper/2604.11344/) (2026)
- [A Hormone-inspired Emotion Layer for Transformer language models (HELT)](https://mlsanity.com/paper/2605.13858/) (2026)
- [DySem: Uncovering Dynamic Semantic Components of Large Language Models for Calculating Semantic Textual Similarity](https://mlsanity.com/paper/2605.29751/) (2026)
- [ReverseEOL: Improving Training-free Text Embeddings via Text Reversal in Decoder-only LLMs](https://mlsanity.com/paper/2606.05858/) (2026)
- [Selecting What Matters: Semantic Compression-Guided Selective Pooling for Long-Context Embeddings](https://mlsanity.com/paper/2609.37782/) (2026)

## Abstract (arXiv)

Extracting sentence embeddings from large language models (LLMs) is a promising direction, as LLMs have demonstrated stronger semantic understanding capabilities. Previous studies typically focus on prompt engineering to elicit sentence embeddings from LLMs by prompting the model to encode sentence information into the embedding of the last token. However, LLMs are mostly decoder-only models with causal attention and the earlier tokens in the sentence cannot attend to the latter tokens, resulting in biased encoding of sentence information and cascading effects on the final decoded token. To this end, we propose a novel Token Prepending (TP) technique that prepends each layer's decoded sentence embedding to the beginning of the sentence in the next layer's input, allowing earlier tokens to attend to the complete sentence information under the causal attention mechanism. The proposed TP technique is a plug-and-play and training-free technique, which means it can be seamlessly integrated with various prompt-based sentence embedding methods and autoregressive LLMs. Extensive experiments on various Semantic Textual Similarity (STS) tasks and downstream classification tasks demonstrate that our proposed TP technique can significantly improve the performance of existing prompt-based sentence embedding methods across different LLMs, while incurring negligible additional inference cost.