Challenge: Recent research shows that fine-tuning dense retrievers to realize their capacity requires carefully designed fine-cuning techniques.
Approach: They propose a pre-training architecture that learns to condense information into the dense vector through LM pre-training and a coCondenser architecture which adds an unsupervised corpus-level contrastive loss to warm up the passage embedding space.
Outcome: The proposed architecture reduces the need for heavy data engineering and large batch training.

Similar Papers

Condenser: a Pre-training Architecture for Dense Retrieval (2021.emnlp-main)

Copied to clipboard

Challenge: Prior work fine-tunes deep LMs to encode text sequences into single dense vector representations, but dense encoders require a lot of data and sophisticated techniques to train and suffer in low data situations.
Approach: They propose to pre-train Transformer language models (LMs) with a novel Transformer architecture, Condenser, where LM prediction CONditions on DENSE Representation.
Outcome: The proposed model improves on various text retrieval and similarity tasks by large margins over standard LMs.
Making Large Language Models Efficient Dense Retrievers (2026.acl-long)

Copied to clipboard

Challenge: Recent studies have shown that fine-tuning large language models for dense retrieval yields strong performance, but their substantial parameter counts make them computationally inefficient.
Approach: They propose a framework for developing efficient retrievers that performs coarse-to-fine compression through a coarse-grained coarse-tuning strategy.
Outcome: The proposed framework reduces model size and inference cost while preserving performance of full-size models.
SimLM: Pre-training with Representation Bottleneck for Dense Passage Retrieval (2023.acl-long)

Copied to clipboard

Challenge: SimLM uses a simple bottleneck architecture that learns to compress the passage information into a dense vector through self-supervised pre-training.
Approach: They propose a simple yet effective pre-training method for dense passage retrieval that learns to compress the passage information into a dense vector through self-supervised pre-tuning.
Outcome: The proposed method outperforms multi-vector approaches on large-scale passage retrieval datasets and shows significant improvements over baselines.
Less is More: Pretrain a Strong Siamese Encoder for Dense Text Retrieval Using a Weak Decoder (2021.emnlp-main)

Copied to clipboard

Challenge: Dense retrieval requires high-quality text sequence embeddings to support effective search in the representation space.
Approach: They propose a self-learning method that pre-trains the autoencoder using a weak decoder to push the encoder to provide better sequence representations.
Outcome: The proposed model significantly boosts the effectiveness and few-shot ability of dense retrieval models on web search, news recommendation, and open domain question answering.
Llama2Vec: Unsupervised Adaptation of Large Language Models for Dense Retrieval (2024.acl-long)

Copied to clipboard

Challenge: Dense retrieval requires discriminative embeddings to represent the semantic relationship between query and document.
Approach: They propose an unsupervised approach that performs unsupervised adaptation of large language models for dense retrieval.
Outcome: The proposed model improves on a variety of dense retrieval benchmarks and is available on github.
Large Language Models as Foundations for Next-Gen Dense Retrieval: A Comprehensive Empirical Assessment (2024.emnlp-main)

Copied to clipboard

Challenge: Pre-trained language models have limited generalization capabilities and performance challenges.
Approach: They evaluate 15 different backbone LLMs and non-LLMs to evaluate their performance . larger models and extensive pre-training consistently enhance in-domain accuracy and data efficiency .
Outcome: The results show that larger models and extensive pre-training enhance in-domain accuracy and data efficiency.
Unsupervised Dense Retrieval with Relevance-Aware Contrastive Pre-Training (2023.findings-acl)

Copied to clipboard

Challenge: Dense retrievers have impressive performance, but their demand for abundant training data limits their application scenarios.
Approach: They propose a method which uses unlabeled data to construct pseudo-positive examples from unlabelled data and then contrastively weighs the contrastive loss of different pairs according to the estimated relevance.
Outcome: The proposed method beats the SOTA unsupervised Contriever model on BEIR and open-domain QA retrieval benchmarks and is a good few-shot learner.
Shall We Pretrain Autoregressive Language Models with Retrieval? A Comprehensive Study (2023.emnlp-main)

Copied to clipboard

Challenge: a recent study shows that retrieval-augmented LMs can improve text generation quality and accuracy.
Approach: They propose a model that reproduces RETRO parameters while retrieving a text corpus . they find RETRO outperforms GPT on text generation with less repetition .
Outcome: The proposed model outperforms standard retrieval-augmented GPT and retrieval augmented GTP on text generation and accuracy tasks.
Dense Passage Retrieval: Is it Retrieving? (2024.findings-emnlp)

Copied to clipboard

Challenge: Large Language Models (LLMs) internally store repositories of knowledge, but access to these repositoriels is imprecise.
Approach: They propose a paradigm called retrieval augmented generation to address hallucinations . they analyze the role of fine-tuning pre-trained networks to enhance alignment .
Outcome: The proposed paradigm addresses hallucinations by fine-tuning pre-trained models . the model can be decentralized, inject facts as decentralized representations .
ExpandR: Teaching Dense Retrievers Beyond Queries with LLM Guidance (2025.emnlp-main)

Copied to clipboard

Challenge: Existing methods for enhancing dense retrieval with query augmentation ignore the alignment between generation and ranking objectives.
Approach: They propose a unified LLM-augmented dense retrieval framework that jointly optimizes both the LLM and the retriever.
Outcome: Experimental results show that ExpandR outperforms strong baselines, achieving more than 5% improvement in retrieval performance.

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