Posts by Collection

Abstract The integration of deep, pre-trained language models, such as BERT, into retrieval and ranking pipelines has shown to provide large effectiveness gains over traditional bag-of-words models in the passage retr...

Abstract

Abstract High-quality medical systematic reviews require comprehensive literature searches to ensure the recommendations and outcomes are sufficiently reliable. Indeed, searching for relevant medical literature is a k...

Abstract Screening or assessing studies is critical to the quality and outcomes of a systematic review. Typically, a Boolean query retrieves the set of studies to screen. As the set of studies retrieved is unordered, ...

Abstract Medical systematic review query formulation is a highly complex task done by trained information specialists. Complexity comes from the reliance on lengthy Boolean queries, which express a detailed research q...

Abstract Current pre-trained language model approaches to information retrieval can be broadly divided into two categories: sparse retrievers (to which belong also non-neural approaches such as bag-of-words methods, e...

Abstract Medical systematic review query formulation is a highly complex task done by trained information specialists. Complexity comes from the reliance on lengthy Boolean queries, which express a detailed research q...

Abstract Medical systematic reviews typically require that all the documents retrieved by a search are assessed. The reason is two-fold: the task aims for “total recall”; and documents retrieved using Boolean search a...

Abstract Boolean query construction is often critical for medical systematic review literature search. To create an effective Boolean query, sys- tematic review researchers typically spend weeks coming up with effecti...

Abstract Knowledge distillation plays a key role in boosting the effectiveness of rankers based on pre-trained language models (PLMs); this is achieved using an effective but inefficient large model to teach a more ef...

Abstract Systematic reviews are comprehensive reviews of the literature for a highly focused research question. These reviews are often treated as the highest form of evidence in evidence-based medicine, and are the k...

Abstract Screening prioritisation in medical systematic reviews aims to rank the set of documents retrieved by complex Boolean queries. The goal is to prioritise the most important documents so that subsequent review ...

Abstract Systematic reviews are crucial for evidence-based medicine as they comprehensively analyse published research findings on specific questions. Conducting such reviews is often resource- and time-intensive, esp...

Abstract Federated search, which involves integrating results from multiple independent search engines, will become increasingly pivotal in the context of Retrieval-Augmented Generation pipelines empowering LLM-based ...

Abstract Federated search systems aggregate results from multiple search engines, selecting appropriate sources to enhance result quality and align with user intent. With the increasing uptake of Retrieval-Augmented G...

Abstract Recent advances in large language models have enabled the development of viable generative information retrieval systems. A generative retrieval system returns a grounded generated text in response to an info...

Abstract Text stemming is a natural language processing technique that is used to reduce words to their base form, also known as the root form. The use of stemming in IR has been shown to often improve the effectivene...

Abstract We provide a systematic understanding of the impact of specific components and wordings used in prompts on the effectiveness of rankers based on zero-shot Large Language Models (LLMs). Several zero-shot ranki...

Abstract Retrieval-Augmented Generation allows to enhance Large Language Models with external knowledge. In response to the recent popularity of generative LLMs, many RAG approaches have been proposed, which involve a...

Abstract Retrieval-Augmented Generation (RAG) allows overcoming the limited knowledge of LLMs by extending the input with external information. As a consequence, the contextual inputs to the model become much longer w...

Abstract Effective approaches that can scale embedding model depth (i.e. layers) and embedding size allow for the creation of models that are highly scalable across different computational resources and task requireme...

Abstract Due to their low efficiency, neural retrieval models are usually evaluated on small corpora (e.g. MS MARCO or BEIR subsets) or in re-ranking scenarios using a more efficient first-stage retriever. To estimate...

Abstract 2D Matryoshka Training is an advanced embedding representation training approach designed to train an encoder model simultaneously across various layer-dimension setups. This method has demonstrated higher ef...

Abstract Systematic reviews are comprehensive literature reviews that address highly focused research questions and represent the highest form of evidence in medicine. A critical step in this process is the developmen...

Abstract Dense retrievers utilize pre-trained backbone language models (e.g., BERT, LLaMA) that are fine-tuned via contrastive learning to perform the task of encoding text into sense representations that can be then ...

Abstract Evaluating complex Retrieval Augmented Generation (RAG) systems in real-world settings is challenging. There is often a lack of finegrained labelled data and the absence of comprehensive evaluation tools tha...

Abstract We present AutoBool, a reinforcement learning (RL) framework that trains large language models (LLMs) to generate effective Boolean queries for medical systematic reviews. Boolean queries are the primary mech...

Abstract Document chunking is a critical preprocessing step in dense retrieval systems, yet the design space of chunking strategies remains poorly understood. Recent research has proposed several concurrent approaches...

Abstract This paper introduces Rank-R1, a novel LLM-based reranker that performs reasoning over both the user query and candidate documents before performing the ranking task. Existing document reranking methods based...

Abstract Large Language Models (LLMs) have emerged as powerful re-rankers. Recent research has shown that simple prompt injections embedded within a candidate document (jailbreak prompt attacks) can significantly alte...

Abstract This paper shows how diffusion language models (DLMs) can be used as effective and efficient retrievers. Existing DLM-based retrievers (e.g., DiffEmbed) follow BERT-style encoding, representing each query or ...

Abstract Recent generative engine optimisation (GEO) research has shown that prompt-injection attacks can push a target product to the top of an LLM’s recommendation list, with the strongest attacks reporting very hig...

Abstract Existing deep-research agents typically follow a search-visit workflow that retrieves whole webpages without using the structure already exposed by titles, headings, sections, and metadata. This limits the ag...