Related papers: Beyond Precision: A Study on Recall of Initial Ret…
Building relevance models to rank documents based on user information needs is a central task in information retrieval and the NLP community. Beyond the direct ad-hoc search setting, many knowledge-intense tasks are powered by a first-stage…
Recently, the retrieval models based on dense representations have been gradually applied in the first stage of the document retrieval tasks, showing better performance than traditional sparse vector space models. To obtain high efficiency,…
Neural ranking models for information retrieval (IR) use shallow or deep neural networks to rank search results in response to a query. Traditional learning to rank models employ machine learning techniques over hand-crafted IR features. By…
Search engines rely heavily on term-based approaches that represent queries and documents as bags of words. Text---a document or a query---is represented by a bag of its words that ignores grammar and word order, but retains word frequency…
Neural Information Retrieval models hold the promise to replace lexical matching models, e.g. BM25, in modern search engines. While their capabilities have fully shone on in-domain datasets like MS MARCO, they have recently been challenged…
Large Language Models (LLMs) have shown strong promise as rerankers, especially in ``listwise'' settings where an LLM is prompted to rerank several search results at once. However, this ``cascading'' retrieve-and-rerank approach is limited…
Multimodal representations and continual learning are two areas closely related to human intelligence. The former considers the learning of shared representation spaces where information from different modalities can be compared and…
Information Retrieval (IR) methods aim to identify documents relevant to a query, which have been widely applied in various natural language tasks. However, existing approaches typically consider only the textual content within documents,…
Given a query and a document corpus, the information retrieval (IR) task is to output a ranked list of relevant documents. Combining large language models (LLMs) with embedding-based retrieval models, recent work shows promising results on…
The state-of-the-art solutions to the vocabulary mismatch in information retrieval (IR) mainly aim at leveraging either the relational semantics provided by external resources or the distributional semantics, recently investigated by deep…
This paper explores a novel technique for improving recall in cross-language information retrieval (CLIR) systems using iterative query refinement grounded in the user's lexical-semantic space. The proposed methodology combines multi-level…
Neural document ranking approaches, specifically transformer models, have achieved impressive gains in ranking performance. However, query processing using such over-parameterized models is both resource and time intensive. In this paper,…
Image retrieval remains a challenging task due to the complex interaction between human visual perception, memory, and computational processes. Current image search engines often struggle to efficiently retrieve images based on natural…
Information retrieval (IR) for precision medicine (PM) often involves looking for multiple pieces of evidence that characterize a patient case. This typically includes at least the name of a condition and a genetic variation that applies to…
Expansion-enhanced sparse lexical representation improves information retrieval (IR) by minimizing vocabulary mismatch problems during lexical matching. In this paper, we explore the potential of jointly learning dense semantic…
Pairing a lexical retriever with a neural re-ranking model has set state-of-the-art performance on large-scale information retrieval datasets. This pipeline covers scenarios like question answering or navigational queries, however, for…
Retrieval-augmented generation (RAG) is a common way to ground language models in external documents and up-to-date information. Classical retrieval systems relied on lexical methods such as BM25, which rank documents by term overlap with…
Retrieval-Augmented Generation (RAG) has emerged as a promising framework to mitigate hallucinations in Large Language Models (LLMs), yet its overall performance is dependent on the underlying retrieval system. In the finance domain,…
Scientific retrieval is essential for advancing scientific knowledge discovery. Within this process, document reranking plays a critical role in refining first-stage retrieval results. However, standard LLM listwise reranking faces…
Addressing the complexity of comprehensive information retrieval, this study introduces an innovative, iterative retrieval-augmented generation system. Our approach uniquely integrates a vector-space driven re-ranking mechanism with…