Challenge: Recent studies have focused on prompt engineering to extract sentence embeddings from large language models (LLMs) but these models are mostly decoder-only and the earlier tokens in the sentence cannot attend to the latter, resulting in biased encoding of sentence information and cascading effects on the final decoded token.
Approach: They propose a plug-and-play and training-free technique that prepends each layer’s decoded sentence embedding to the beginning of the sentence in the next layer’ s input.
Outcome: The proposed technique can significantly improve the performance of existing prompt-based sentence embedding methods across different LLMs while incurring negligible additional inference cost.

Similar Papers

Hierarchical Token Prepending: Enhancing Information Flow in Decoder-based LLM Embeddings (2026.acl-long)

Copied to clipboard

Challenge: Large language models produce powerful text embeddings, but their causal attention mechanism restricts the flow of information from later to earlier tokens, harming performance.
Approach: They propose a method that prepending a single summary token to reduce attention-level compression by partitioning the input into blocks and prepending blocks to subsequent blocks.
Outcome: The proposed method achieves consistent performance gains across 11 retrieval datasets and 30 general embedding benchmarks.
Contrastive Prompting Enhances Sentence Embeddings in LLMs through Inference-Time Steering (2025.acl-long)

Copied to clipboard

Challenge: Existing studies focus on prompt engineering to encode the full semantics of a sentence into the embedding of the last token.
Approach: They propose a technique that introduces an extra auxiliary prompt to elicit better sentence embedding . they propose to use the hidden state of the token as the sentence embedded in LLMs .
Outcome: The proposed technique can improve performance of existing prompt-based methods on STS tasks and downstream classification tasks.
Causal2Vec: Improving Decoder-only LLMs as Embedding Models through a Contextual Token (2026.acl-long)

Copied to clipboard

Challenge: Existing methods modify attention mechanism to be bidirectional, undermining LLMs’ ability to extract semantic information acquired during pre-training.
Approach: They propose a general-purpose embedding model that pre-encodes input text into a single Contextual token and then prepends it to the LLM's input sequence.
Outcome: The proposed model improves performance of decoder-only large language models without altering their architectures or introducing significant computational overhead.
GenEOL: Harnessing the Generative Power of LLMs for Training-Free Sentence Embeddings (2025.findings-naacl)

Copied to clipboard

Challenge: Training-free embedding methods focus on optimizing embeddable prompts . previous methods have overlooked the benefits of utilizing generative abilities of LLMs - GenEOL .
Approach: They propose a method that leverages pretrained large language models to embed text . they propose generating diverse transformations of a sentence that preserve its meaning .
Outcome: The proposed method outperforms existing training-free embedding methods by 2.85 points on the sentence semantic text similarity (STS) benchmark.
A Text is Worth Several Tokens: Text Embedding from LLMs Secretly Aligns Well with The Key Tokens (2025.acl-long)

Copied to clipboard

Challenge: et al., 2023) show that text embeddings from large language models can be aligned with key tokens in input text.
Approach: They propose a sparse retrieval method based on aligned tokens for large language models . they show that this phenomenon is universal and is not affected by model architecture .
Outcome: The proposed method can achieve 80% of the dense retrieval effect of the same model while reducing the computation significantly.
KV-Embedding: Training-free Text Embedding via Internal KV Re-routing in Decoder-only LLMs (2026.acl-long)

Copied to clipboard

Challenge: Recent work shows that decoder-only LLMs can serve as strong embedding backbones when fine-tuned with contrastive objectives.
Approach: They propose a framework that activates the latent representation power of frozen LLMs by rerouting the final token's KV states as a prepended prefix.
Outcome: The proposed framework outperforms existing training-free baselines by 10% on MTEB and maintains robust performance on sequences up to 4,096 tokens.
Going Beyond Sentence Embeddings: A Token-Level Matching Algorithm for Calculating Semantic Textual Similarity (2023.acl-short)

Copied to clipboard

Challenge: Semantic Textual Similarity (STS) measures the degree to which the underlying semantics of paired sentences are equivalent.
Approach: They propose a token-level matching inference algorithm which can be applied on top of any language model to improve its performance on STS task.
Outcome: The proposed method improves the performance of almost all language models, with up to 12.7% gain in Spearman’s correlation.
SemPA: Improving Sentence Embeddings of Large Language Models through Semantic Preference Alignment (2026.findings-acl)

Copied to clipboard

Challenge: Existing sentence embedding methods rely on fixed prompt templates or involve modifications to the model architecture, compromising its generative capabilities.
Approach: They propose a sentence-level direct preference optimization approach that boosts the sentence representations while preserving the generative ability of LLMs.
Outcome: The proposed method improves representations of semantically meaningful vectors without sacrificing generation capability.
Learning to Insert [PAUSE] Tokens for Better Reasoning (2025.findings-acl)

Copied to clipboard

Challenge: Existing studies have explored incorporating special-purpose tokens into the training process to enhance reasoning capabilities.
Approach: They propose a method for inserting dummy tokens consecutively just before reasoning steps to increase model effectiveness.
Outcome: The proposed method outperforms fine-tuning and previous token insertion methods on multiple datasets and models.
T-FREE: Subword Tokenizer-Free Generative LLMs via Sparse Representations for Memory-Efficient Embeddings (2024.emnlp-main)

Copied to clipboard

Challenge: Tokenizers are crucial for encoding information in Large Language Models, but their development has stagnated.
Approach: They propose a tokenizer that embeds words through sparse activation patterns over character triplets . they show competitive downstream performance with a parameter reduction of more than 85% .
Outcome: The proposed approach achieves competitive downstream performance with a parameter reduction of more than 85% on embedding layers.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations