# Making Large Language Models Efficient Dense Retrievers

arXiv: https://arxiv.org/abs/2512.20612 · HTML: https://mlsanity.com/paper/2512.20612/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 42 references that are in the map.
- First posted on arXiv 23 Dec 2025.

## Builds on (most cited first, 30 of 31)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [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)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [Locating and Editing Factual Associations in GPT](https://mlsanity.com/paper/2202.05262/) (2022)
- [Gemma 2: Improving Open Language Models at a Practical Size](https://mlsanity.com/paper/2408.00118/) (2024)
- [MS MARCO: A Human Generated MAchine Reading COmprehension Dataset](https://mlsanity.com/paper/1611.09268/) (2016)
- [Text Embeddings by Weakly-Supervised Contrastive Pre-training](https://mlsanity.com/paper/2212.03533/) (2022)
- [BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models](https://mlsanity.com/paper/2104.08663/) (2021)
- [Unsupervised Dense Information Retrieval with Contrastive Learning](https://mlsanity.com/paper/2112.09118/) (2021)
- [SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot](https://mlsanity.com/paper/2301.00774/) (2023)
- [M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation](https://mlsanity.com/paper/2402.03216/) (2024)
- [Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval](https://mlsanity.com/paper/2007.00808/) (2020)
- [Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning](https://mlsanity.com/paper/2310.06694/) (2023)
- [Fine-Tuning LLaMA for Multi-Stage Text Retrieval](https://mlsanity.com/paper/2310.08319/) (2023)
- [Efficiently Teaching an Effective Dense Retriever with Balanced Topic Aware Sampling](https://mlsanity.com/paper/2104.06967/) (2021)
- [The Unreasonable Ineffectiveness of the Deeper Layers](https://mlsanity.com/paper/2403.17887/) (2024)
- [Modifying Memories in Transformer Models](https://mlsanity.com/paper/2012.00363/) (2020)
- [What Matters in Transformers? Not All Attention is Needed](https://mlsanity.com/paper/2406.15786/) (2024)
- [Making Text Embedders Few-Shot Learners](https://mlsanity.com/paper/2409.15700/) (2024)
- [Promptriever: Instruction-Trained Retrievers Can Be Prompted Like Language Models](https://mlsanity.com/paper/2409.11136/) (2024)
- [Unsupervised Dense Retrieval with Relevance-Aware Contrastive Pre-Training](https://mlsanity.com/paper/2306.03166/) (2023)
- [Efficient Inverted Indexes for Approximate Retrieval over Learned Sparse Representations](https://mlsanity.com/paper/2404.18812/) (2024)
- [A deeper look at depth pruning of LLMs](https://mlsanity.com/paper/2407.16286/) (2024)
- [MAIR: A Massive Benchmark for Evaluating Instructed Retrieval](https://mlsanity.com/paper/2410.10127/) (2024)
- [Large Language Models as Foundations for Next-Gen Dense Retrieval: A Comprehensive Empirical Assessment](https://mlsanity.com/paper/2408.12194/) (2024)
- [DRAMA: Diverse Augmentation from Large Language Models to Smaller Dense Retrievers](https://mlsanity.com/paper/2502.18460/) (2025)
- [Starbucks-v2: Improved Training for 2D Matryoshka Embeddings](https://mlsanity.com/paper/2410.13230/) (2024)

## Built on by (most cited first, 3 of 3)

- [Invariant Pretraining for Robust Code Representations](https://mlsanity.com/paper/2608.15412/) (2026)
- [Mixture-of-Experts Language Models Can Be Strong and Efficient Retrievers](https://mlsanity.com/paper/2609.13486/) (2026)
- [Your Transformer Is Secretly Elastic](https://mlsanity.com/paper/2610.20588/) (2026)

## Abstract (arXiv)

Recent work has shown that directly fine-tuning large language models (LLMs) for dense retrieval yields strong performance, but their substantial parameter counts make them computationally inefficient. While prior studies have revealed significant layer redundancy in LLMs for generative tasks, it remains unclear whether similar redundancy exists when these models are adapted for retrieval tasks, which require encoding entire sequences into fixed representations rather than generating tokens iteratively. To this end, we conduct a comprehensive analysis of layer redundancy in LLM-based dense retrievers. We find that, in contrast to generative settings, MLP layers are substantially more prunable, while attention layers remain critical for semantic aggregation. Building on this insight, we propose EffiR, a framework for developing efficient retrievers that performs large-scale MLP compression through a coarse-to-fine strategy (coarse-grained depth reduction followed by fine-grained width reduction), combined with retrieval-specific fine-tuning. Across diverse BEIR datasets and LLM backbones, EffiR achieves substantial reductions in model size and inference cost while preserving the performance of full-size models.