Related papers: Low-Resource Dense Retrieval for Open-Domain Quest…

Deep prompt tuning (DPT) has gained great success in most natural language processing~(NLP) tasks. However, it is not well-investigated in dense retrieval where fine-tuning~(FT) still dominates. When deploying multiple retrieval tasks using…

Building effective dense retrieval systems remains difficult when relevance supervision is not available. Recent work has looked to overcome this challenge by using a Large Language Model (LLM) to generate hypothetical documents that can be…

In this paper, we systematically study the potential of pre-training with Large Language Model(LLM)-based document expansion for dense passage retrieval. Concretely, we leverage the capabilities of LLMs for document expansion, i.e. query…

The drafting of documents in the procurement field has progressively become more complex and diverse, driven by the need to meet legal requirements, adapt to technological advancements, and address stakeholder demands. While large language…

Pretrained language models like BERT and T5 serve as crucial backbone encoders for dense retrieval. However, these models often exhibit limited generalization capabilities and face challenges in improving in domain accuracy. Recent research…

Promptagator demonstrated that Large Language Models (LLMs) with few-shot prompts can be used as task-specific query generators for fine-tuning domain-specialized dense retrieval models. However, the original Promptagator approach relied on…

Electronic Health Records (EHRs) are pivotal in clinical practices, yet their retrieval remains a challenge mainly due to semantic gap issues. Recent advancements in dense retrieval offer promising solutions but existing models, both…

Recent advancements in Large Language Models (LLMs) have significantly improved their performance across various Natural Language Processing (NLP) tasks. However, LLMs still struggle with generating non-factual responses due to limitations…

Learned sparse retrieval (LSR) is a family of neural retrieval methods that transform queries and documents into sparse weight vectors aligned with a vocabulary. While LSR approaches like Splade work well for short passages, it is unclear…

Function calling agents powered by Large Language Models (LLMs) select external tools to automate complex tasks. On-device agents typically use a retrieval module to select relevant tools, improving performance and reducing context length.…

The performance of Dense retrieval (DR) is significantly influenced by the quality of negative sampling. Traditional DR methods primarily depend on naive negative sampling techniques or on mining hard negatives through external retriever…

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…

Large Language Models (LLMs) often generate inaccurate responses (hallucinations) when faced with questions beyond their knowledge scope. Retrieval-Augmented Generation (RAG) addresses this by leveraging external knowledge, but a critical…

We present an end-to-end differentiable training method for retrieval-augmented open-domain question answering systems that combine information from multiple retrieved documents when generating answers. We model retrieval decisions as…

Relation Extraction (RE) serves as a crucial technology for transforming unstructured text into structured information, especially within the framework of Knowledge Graph development. Its importance is emphasized by its essential role in…

Pre-trained language models (PLMs) have proven to be effective for document re-ranking task. However, they lack the ability to fully interpret the semantics of biomedical and health-care queries and often rely on simplistic patterns for…

One of the core problems in large-scale recommendations is to retrieve top relevant candidates accurately and efficiently, preferably in sub-linear time. Previous approaches are mostly based on a two-step procedure: first learn an…

Dense retrieval approaches can overcome the lexical gap and lead to significantly improved search results. However, they require large amounts of training data which is not available for most domains. As shown in previous work (Thakur et…

Most state-of-the-art open-domain question answering systems use a neural retrieval model to encode passages into continuous vectors and extract them from a knowledge source. However, such retrieval models often require large memory to run…

Dense retrieval has shown promise in the first-stage retrieval process when trained on in-domain labeled datasets. However, previous studies have found that dense retrieval is hard to generalize to unseen domains due to its weak modeling of…