Related papers: Adversarial Retriever-Ranker for dense text retrie…

Retrieval augmented generation (RAG) has been widely adopted to help Large Language Models (LLMs) to process tasks involving long documents. However, existing retrieval models are not designed for long document retrieval and fail to address…

We show the sup-norm convergence of deep neural network estimators with a novel adversarial training scheme. For the nonparametric regression problem, it has been shown that an estimator using deep neural networks can achieve better…

Image retrieval is a crucial research topic in computer vision, with broad application prospects ranging from online product searches to security surveillance systems. In recent years, the accuracy and efficiency of image retrieval have…

In recent years, the learned local descriptors have outperformed handcrafted ones by a large margin, due to the powerful deep convolutional neural network architectures such as L2-Net [1] and triplet based metric learning [2]. However,…

E-commerce information retrieval (IR) systems struggle to simultaneously achieve high accuracy in interpreting complex user queries and maintain efficient processing of vast product catalogs. The dual challenge lies in precisely matching…

Retrieval augmented generation (RAG) has been applied in many scenarios to augment large language models (LLMs) with external documents provided by retrievers. However, a semantic gap exists between LLMs and retrievers due to differences in…

Retrieval-augmented generation (RAG) systems combine large language models (LLMs) with external knowledge retrieval, making them highly effective for knowledge-intensive tasks. A crucial but often under-explored component of these systems…

Adversarial training (AT) as a regularization method has proved its effectiveness in various tasks, such as image classification and text classification. Though there are successful applications of AT in many tasks of natural language…

Retrieving procedure-oriented evidence from materials science papers is difficult because key synthesis details are often scattered across long, context-heavy documents and are not well captured by paragraph-only dense retrieval. We present…

We study cross-lingual sequence tagging with little or no labeled data in the target language. Adversarial training has previously been shown to be effective for training cross-lingual sentence classifiers. However, it is not clear if…

Rerankers, typically cross-encoders, are computationally intensive but are frequently used because they are widely assumed to outperform cheaper initial IR systems. We challenge this assumption by measuring reranker performance for full…

Recently, generative adversarial networks and adversarial autoencoders have gained a lot of attention in machine learning community due to their exceptional performance in tasks such as digit classification and face recognition. They map…

State-of-the-art neural models typically encode document-query pairs using cross-attention for re-ranking. To this end, models generally utilize an encoder-only (like BERT) paradigm or an encoder-decoder (like T5) approach. These paradigms,…

Adversarial training has shown impressive success in learning bilingual dictionary without any parallel data by mapping monolingual embeddings to a shared space. However, recent work has shown superior performance for non-adversarial…

Contextual representations learned by language models can often encode undesirable attributes, like demographic associations of the users, while being trained for an unrelated target task. We aim to scrub such undesirable attributes and…

InfoNCE loss is commonly used to train dense retriever in information retrieval tasks. It is well known that a large batch is essential to stable and effective training with InfoNCE loss, which requires significant hardware resources. Due…

Recent works in relation extraction (RE) have achieved promising benchmark accuracy; however, our adversarial attack experiments show that these works excessively rely on entities, making their generalization capability questionable. To…

We propose an adversarial deep reinforcement learning (ADRL) algorithm for high-dimensional stochastic control problems. Inspired by the information relaxation duality, ADRL reformulates the control problem as a min-max optimization between…

Information retrieval involves selecting artifacts from a corpus that are most relevant to a given search query. The flavor of retrieval typically used in classical applications can be termed as homogeneous and relaxed, where queries and…

A wireless communications system usually consists of a transmitter which transmits the information and a receiver which recovers the original information from the received distorted signal. Deep learning (DL) has been used to improve the…