Related papers: Improving Dense Passage Retrieval with Multiple Po…

It has been shown that dual encoders trained on one domain often fail to generalize to other domains for retrieval tasks. One widespread belief is that the bottleneck layer of a dual encoder, where the final score is simply a dot-product…

The information retrieval community has made significant progress in improving the efficiency of Dual Encoder (DE) dense passage retrieval systems, making them suitable for latency-sensitive settings. However, many proposed procedures are…

Ranking responses for a given dialogue context is a popular benchmark in which the setup is to re-rank the ground-truth response over a limited set of $n$ responses, where $n$ is typically 10. The predominance of this setup in conversation…

Successful video analysis relies on accurate recognition of pixels across frames, and frame reconstruction methods based on video correspondence learning are popular due to their efficiency. Existing frame reconstruction methods, while…

Recently, retrieval systems based on dense representations have led to important improvements in open-domain question answering, and related tasks. While very effective, this approach is also memory intensive, as the dense vectors for the…

High-throughput computational imaging requires efficient processing algorithms to retrieve multi-dimensional and multi-scale information. In computational phase imaging, phase retrieval (PR) is required to reconstruct both amplitude and…

We propose a simple, unsupervised method that injects pragmatic principles in retrieval-augmented generation (RAG) frameworks such as Dense Passage Retrieval to enhance the utility of retrieved contexts. Our approach first identifies which…

The integration of retrieved passages and large language models (LLMs), such as ChatGPTs, has significantly contributed to improving open-domain question answering. However, there is still a lack of exploration regarding the optimal…

Text-to-Video Retrieval (TVR) is essential in video platforms. Dense retrieval with dual-modality encoders leads in accuracy, but its computation and storage scale poorly with corpus size. Thus, real-time large-scale applications adopt…

Recently, methods have been developed to improve the performance of dense passage retrieval by using context-supervised pre-training. These methods simply consider two passages from the same document to be relevant, without taking into…

Over recent years, an increasing amount of compute and data has been poured into training large language models (LLMs), usually by doing one-pass learning on as many tokens as possible randomly selected from large-scale web corpora. While…

Legal Passage Retrieval (LPR) systems are crucial as they help practitioners save time when drafting legal arguments. However, it remains an underexplored avenue. One primary reason is the significant vocabulary mismatch between the query…

The DEtection TRansformer (DETR) is a powerful end-to-end object detector, yet its one-to-one matching strategy suffers from slow convergence and low recall. A common approach to address this issue is to use one-to-many label assignment to…

Masked auto-encoder pre-training has emerged as a prevalent technique for initializing and enhancing dense retrieval systems. It generally utilizes additional Transformer decoder blocks to provide sustainable supervision signals and…

The goal of screening prioritisation in systematic reviews is to identify relevant documents with high recall and rank them in early positions for review. This saves reviewing effort if paired with a stopping criterion, and speeds up review…

Retrieval-augmented generation (RAG) has been widely adopted to augment large language models (LLMs) with external knowledge for knowledge-intensive tasks. However, its effectiveness is often undermined by the presence of noisy (i.e.,…

Many recent approaches of passage retrieval are using dense embeddings generated from deep neural models, called "dense passage retrieval". The state-of-the-art end-to-end dense passage retrieval systems normally deploy a deep neural model…

Retrieval-augmented Generation (RAG) is powerful, but its effectiveness hinges on which retrievers we use and how. Different retrievers offer distinct, often complementary signals: BM25 captures lexical matches; dense retrievers, semantic…

Retrieval-Augmented Generation (RAG) enhances Large Language Models (LLMs) by integrating external knowledge bases, achieving state-of-the-art results in various coding tasks. The core of RAG is retrieving demonstration examples, which is…

Sparse lexical representation learning has demonstrated much progress in improving passage retrieval effectiveness in recent models such as DeepImpact, uniCOIL, and SPLADE. This paper describes a straightforward yet effective approach for…