Hybrid-Vector Retrieval for Visually Rich Documents: Combining Single-Vector Efficiency and Multi-Vector Accuracy (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to document retrieval are coarse and efficient, but expensive. |
| Approach: | a plug-and-play two-stage hybrid-vector framework is proposed to retrieve visually rich documents . HEAVEN efficiently retrieves candidate pages using a single-vektor method over VS-Pages . it also reranks candidates with a multi-vecctor method while filtering query tokens by linguistic importance . |
| Outcome: | HEAVEN achieves 99.87% of the Recall@1 performance of multi-vector models on average . it reduces per-query computation by 99.8%, achieving efficiency and accuracy . |
Similar Papers
Sculpting the Vector Space: Towards Efficient Multi-Vector Visual Document Retrieval via Prune-then-Merge Framework (2026.findings-acl)
Copied to clipboard
| Challenge: | Visual Document Retrieval (VDR) is of importance in multimodal retrieval applications. |
| Approach: | They propose a two-stage pruning and merging frameworks that combine pruning and merge techniques to achieve higher compression rates. |
| Outcome: | The proposed framework outperforms existing methods on 29 visual document retrieval datasets. |
SCV: Light and Effective Multi-Vector Retrieval with Sequence Compressive Vectors (2025.coling-industry)
Copied to clipboard
| Challenge: | Recent advances in language models (LMs) have driven progress in information retrieval (IR), effectively extracting semantically relevant information. |
| Approach: | They propose a multi-vector retrieval framework with sequence compression vectors and a coarse-to-fine vector search framework that uses span compressive vectors to score documents. |
| Outcome: | The proposed approach achieves the fastest latency compared to other state-of-the-art models and can obtain competitive performance on both in-domain and out-of domain benchmark datasets. |
XTR meets ColBERTv2: Adding ColBERTv2 Optimizations to XTR (2025.coling-industry)
Copied to clipboard
| Challenge: | XTR eliminates the need for multi-stage retrieval, but doesn't incorporate efficiency optimizations from ColBERTv2 which improve indexing and retrieval speed. |
| Approach: | They propose a multi-vector retrieval method that simplifies retrieval into a single stage through a modified learning objective. |
| Outcome: | The proposed method eliminates the need for multistage retrieval but doesn't incorporate efficiency optimizations from ColBERTv2 which improve indexing and retrieval speed. |
Pseudo-Relevance for Enhancing Document Representation (2022.emnlp-main)
Copied to clipboard
| Challenge: | a novel approach to document retrieval can be used to encode documents as vectors . a few query-relevant terms can be pruned out to reduce index overhead . |
| Approach: | They propose to enhance the document representation for the bi-encoder approach in dense document retrieval. |
| Outcome: | The proposed solution reduces latency and memory footprint up to 8- and 3-fold . it is validated on MSMARCO and real-world search query logs . |
Sparse, Dense, and Attentional Representations for Text Retrieval (2021.tacl-1)
Copied to clipboard
| Challenge: | Dual encoders perform retrieval by encoding documents and queries into dense low-dimensional vectors, scoring each document by its inner product with the query. |
| Approach: | They propose a dual-encoder-based neural model that combines the efficiency of dual encoders with expressiveness of more costly attentional architectures. |
| Outcome: | The proposed model outperforms strong alternatives in large-scale retrieval. |
Investigating Multi-layer Representations for Dense Passage Retrieval (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Dense retrieval models adopt vectors from the last hidden layer of the document encoder to represent a document, which is in contrast to the fact that representations in different layers of a pre-trained language model contain different kinds of linguistic knowledge and behave differently during fine-tuning. |
| Approach: | They propose to utilize representations from multiple encoder layers to make up the representation of a document, which they denote Multi-layer Representations (MLR). |
| Outcome: | The proposed model outperforms dual encoder, ME-BERT and ColBERT in the single-vector retrieval setting and with other advanced training techniques. |
Multi-View Document Representation Learning for Open-Domain Dense Retrieval (2022.acl-long)
Copied to clipboard
| Challenge: | Existing methods for dense retrieval are hard to match with multiple views. |
| Approach: | They propose a multi-view document representation learning framework to generate multiple embeddings through viewers to represent documents and enforce them to align with different queries. |
| Outcome: | The proposed method outperforms recent works and achieves state-of-the-art results. |
Multi-Vector Attention Models for Deep Re-ranking (2021.emnlp-main)
Copied to clipboard
| Challenge: | Document retrieval systems often use two styles of neural network models . dual encoder models are used for retrieval and deep re-ranking, while cross-attention models are typically used for shallow reranking. |
| Approach: | They propose a dual encoder and cross-attention neural network architectures that combine query and document representations to optimize retrieval accuracy. |
| Outcome: | The proposed architecture trades off retrieval accuracy with joint computation and offline document storage cost. |
Retrieve Fast, Rerank Smart: Cooperative and Joint Approaches for Improved Cross-Modal Retrieval (2022.tacl-1)
Copied to clipboard
| Challenge: | Current approaches to cross-modal retrieval process text and visual input jointly . current approaches are pretrained from scratch and suffer from huge retrieval latency and inefficiency issues . |
| Approach: | They propose a cooperative retrieve-and-rerank framework that turns pretrained text-image multi-modal models into efficient retrieval models. |
| Outcome: | The proposed framework improves retrieval performance over current approaches . it uses twin networks to encode all items of a corpus and a cross-encoder component for a more nuanced ranking . |
Vision-Free Retrieval: Rethinking Multimodal Search with Textual Scene Descriptions (2025.emnlp-main)
Copied to clipboard
| Challenge: | Contrastively trained Vision-Language Models exhibit shallow language understanding, manifesting bag-of-words behaviour. |
| Approach: | They propose a vision-free, single-encoder retrieval pipeline to replace traditional text-to-image retrieval paradigm with structured image descriptions. |
| Outcome: | The proposed approach reduces the modality gap and improves compositionality and performance on short and long caption queries. |