# Enhancing Lexicon-Based Text Embeddings with Large Language Models

arXiv: https://arxiv.org/abs/2501.09749 · HTML: https://mlsanity.com/paper/2501.09749/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 59 references that are in the map.
- First posted on arXiv 16 Jan 2025.

## Builds on (most cited first, 30 of 35)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [MS MARCO: A Human Generated MAchine Reading COmprehension Dataset](https://mlsanity.com/paper/1611.09268/) (2016)
- [FEVER: a large-scale dataset for Fact Extraction and VERification](https://mlsanity.com/paper/1803.05355/) (2018)
- [M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation](https://mlsanity.com/paper/2402.03216/) (2024)
- [SemEval-2017 Task 1: Semantic Textual Similarity - Multilingual and Cross-lingual Focused Evaluation](https://mlsanity.com/paper/1708.00055/) (2017)
- [Towards General Text Embeddings with Multi-stage Contrastive Learning](https://mlsanity.com/paper/2308.03281/) (2023)
- [ELI5: Long Form Question Answering](https://mlsanity.com/paper/1907.09190/) (2019)
- [NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Models](https://mlsanity.com/paper/2405.17428/) (2024)
- [Efficient Intent Detection with Dual Sentence Encoders](https://mlsanity.com/paper/2003.04807/) (2020)
- [SPECTER: Document-level Representation Learning using Citation-informed Transformers](https://mlsanity.com/paper/2004.07180/) (2020)
- [LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders](https://mlsanity.com/paper/2404.05961/) (2024)
- [SPLADE: Sparse Lexical and Expansion Model for First Stage Ranking](https://mlsanity.com/paper/2107.05720/) (2021)
- [Generative Representational Instruction Tuning](https://mlsanity.com/paper/2402.09906/) (2024)
- [MTOP: A Comprehensive Multilingual Task-Oriented Semantic Parsing Benchmark](https://mlsanity.com/paper/2008.09335/) (2020)
- [Llama2Vec: Unsupervised Adaptation of Large Language Models for Dense Retrieval](https://mlsanity.com/paper/2312.15503/) (2023)
- [AIR-Bench 2024: A Safety Benchmark Based on Risk Categories from Regulations and Policies](https://mlsanity.com/paper/2407.17436/) (2024)
- [SPLADE-v3: New baselines for SPLADE](https://mlsanity.com/paper/2403.06789/) (2024)
- [A Few Brief Notes on DeepImpact, COIL, and a Conceptual Framework for Information Retrieval Techniques](https://mlsanity.com/paper/2106.14807/) (2021)
- [Learning Passage Impacts for Inverted Indexes](https://mlsanity.com/paper/2104.12016/) (2021)
- [I Wish I Would Have Loved This One, But I Didn't -- A Multilingual Dataset for Counterfactual Detection in Product Reviews](https://mlsanity.com/paper/2104.06893/) (2021)
- [PromptReps: Prompting Large Language Models to Generate Dense and Sparse Representations for Zero-Shot Document Retrieval](https://mlsanity.com/paper/2404.18424/) (2024)
- [A Proposed Conceptual Framework for a Representational Approach to Information Retrieval](https://mlsanity.com/paper/2110.01529/) (2021)
- [Fast Passage Re-ranking with Contextualized Exact Term Matching and Efficient Passage Expansion](https://mlsanity.com/paper/2108.08513/) (2021)
- [UnifieR: A Unified Retriever for Large-Scale Retrieval](https://mlsanity.com/paper/2205.11194/) (2022)
- [A Unified Framework for Learned Sparse Retrieval](https://mlsanity.com/paper/2303.13416/) (2023)
- [DiSCo: LLM Knowledge Distillation for Efficient Sparse Retrieval in Conversational Search](https://mlsanity.com/paper/2410.14609/) (2024)
- [Mistral-SPLADE: LLMs for better Learned Sparse Retrieval](https://mlsanity.com/paper/2408.11119/) (2024)

## Built on by (most cited first, 6 of 6)

- [Milco: Learned Sparse Retrieval Across Languages via a Multilingual Connector](https://mlsanity.com/paper/2510.00671/) (2025)
- [Rethinking the Privacy of Text Embeddings: A Reproducibility Study of "Text Embeddings Reveal (Almost) As Much As Text"](https://mlsanity.com/paper/2507.07700/) (2025)
- [Benchmarking Filtered Approximate Nearest Neighbor Search Algorithms on Transformer-based Embedding Vectors](https://mlsanity.com/paper/2507.21989/) (2025)
- [AttnCache: Accelerating Self-Attention Inference for LLM Prefill via Attention Cache](https://mlsanity.com/paper/2510.25979/) (2025)
- [LMAR: Language Model Augmented Retriever for Domain-specific Knowledge Indexing](https://mlsanity.com/paper/2508.05672/) (2025)
- [Why Advanced Encoders Lag on Sparse Retrieval? The Answer and an Approach to Bridging Vocabulary Gaps](https://mlsanity.com/paper/2607.00004/) (2026)

## Abstract (arXiv)

Recent large language models (LLMs) have demonstrated exceptional performance on general-purpose text embedding tasks. While dense embeddings have dominated related research, we introduce the first lexicon-based embeddings (LENS) leveraging LLMs that achieve competitive performance on these tasks. LENS consolidates the vocabulary space through token embedding clustering to handle the issue of token redundancy in LLM vocabularies. To further improve performance, we investigate bidirectional attention and various pooling strategies. Specifically, LENS simplifies lexical matching with redundant vocabularies by assigning each dimension to a specific token cluster, where semantically similar tokens are grouped together. Extensive experiments demonstrate that LENS outperforms dense embeddings on the Massive Text Embedding Benchmark (MTEB), delivering compact representations with dimensionality comparable to dense counterparts. Furthermore, LENS inherently supports efficient embedding dimension pruning without any specialized objectives like Matryoshka Representation Learning. Notably, combining LENS with dense embeddings achieves state-of-the-art performance on the retrieval subset of MTEB (i.e., BEIR).