相关论文: Relevance as Deduction: A Logical View of Informat…

Identification of appropriate supporting evidence is critical to the success of scientific fact checking. However, existing approaches rely on off-the-shelf Information Retrieval algorithms that rank documents based on relevance rather than…

In this work, we focus on the problem of retrieving relevant arguments for a query claim covering diverse aspects. State-of-the-art methods rely on explicit mappings between claims and premises, and thus are unable to utilize large…

Most if not all on-line item-to-item recommendation systems rely on estimation of a distance like measure (rank) of similarity between items. For on-line recommendation systems, time sensitivity of this similarity measure is extremely…

Retrieval plays a central role in multi-hop question answering (QA), where answering complex questions requires gathering multiple pieces of evidence. We introduce an Agentic Retrieval System that leverages large language models (LLMs) in a…

This article shows a form of measuring semantic informativity of deductions. Dynamic concepts of complexity and relevancy are presented according to explicit definitions of insertion and deletion on databases. Hence, with respect to finite…

Text retrieval is a long-standing research topic on information seeking, where a system is required to return relevant information resources to user's queries in natural language. From classic retrieval methods to learning-based ranking…

Research has been devoted in the past few years to relevance feedback as an effective solution to improve performance of information retrieval systems. Relevance feedback refers to an interactive process that helps to improve the retrieval…

Information Retrieval (IR) systems are exposed to constant changes in most components. Documents are created, updated, or deleted, the information needs are changing, and even relevance might not be static. While it is generally expected…

Pseudo-relevance feedback (PRF) is commonly used to boost the performance of traditional information retrieval (IR) models by using top-ranked documents to identify and weight new query terms, thereby reducing the effect of query-document…

An operationalistic scheme, called Melucci metaphor, is suggested representing Information Retrieval as physical measurements with beam of particles playing the role of the flow of retrieved documents. The possibilities of query expansion…

Deduction is the one of the major forms of inferences and commonly used in formal logic. This kind of inference has the feature of monotonicity, which can be problematic. There are different types of inferences that are not monotonic, e.g.…

In simple open-domain question answering (QA), dense retrieval has become one of the standard approaches for retrieving the relevant passages to infer an answer. Recently, dense retrieval also achieved state-of-the-art results in multi-hop…

Learning is a distinctive feature of intelligent behaviour. High-throughput experimental data and Big Data promise to open new windows on complex systems such as cells, the brain or our societies. Yet, the puzzling success of Artificial…

We introduce and define the novel problem of multi-distribution information retrieval (IR) where given a query, systems need to retrieve passages from within multiple collections, each drawn from a different distribution. Some of these…

We propose RecaLLM, a set of reasoning language models post-trained to make effective use of long-context information. In-context retrieval, which identifies relevant evidence from context, and reasoning are deeply intertwined: retrieval…

We generalize the notion of consequence relation standard in abstract treatments of logic to accommodate intuitions of relevance. The guiding idea follows the \emph{use criterion}, according to which in order for some premises to have some…

The rise of large language models (LLMs) has significantly transformed both the construction and application of information retrieval (IR) systems. However, current interactions between IR systems and LLMs remain limited, with LLMs merely…

Reranking documents based on their relevance to a given query is a critical task in information retrieval. Traditional reranking methods often lack transparency and rely on proprietary models, hindering reproducibility and interpretability.…

The goal of a technology-assisted review is to achieve high recall with low human effort. Continuous active learning algorithms have demonstrated good performance in locating the majority of relevant documents in a collection, however their…

While dense retrieval models, which embed queries and documents into a shared low-dimensional space, have gained widespread popularity, they were shown to exhibit important theoretical limitations and considerably lag behind traditional…