The standard approach for identifying studies for reviews has remained consistent for many years. This approach can be time-consuming, with quality reliant on searcher skill. Alternate approaches aiming to improve efficiency have been proposed, but there is uncertainty around their performance. To inform searching conduct, we systematically reviewed studies comparing alternate and standard search approaches. We searched PubMed and the Library, Information Science and Technology Abstracts (LISTA) databases on 22 January 2025, browsed the Summarized Research in Information Retrieval for HTA (SuRe Info) website, reviewed reference lists of reviews and book chapters, and conducted a backwards and forwards citation search of included studies. Risk of bias (RoB) was assessed using a modified version of Quality Assessment of Diagnostic Accuracy Studies tool version 2 (QUADAS-2), and alternate approaches were categorised according to whether they potentially (1) improved search conduct, (2) worsened search conduct, or (3) had an impact that was difficult to interpret. We identified 3,520 records and included 14 studies evaluating 12 alternative search approaches. We identified four approaches that potentially improve searches, six which may make searches worse, and two with difficult to interpret results. Most studies had high or unclear RoB arising from the standard search conduct and concern regarding the applicability of the results. Searches may be improved by (1) using seed studies to design searches; (2) adding study design filters; (3) adding backwards citation searching; (4) using automation tools for translating searches across databases. More robust evaluations are needed before we can make stronger recommendations.

This study examines how engineers formulate natural language prompts for searching existing assemblies in mechanical design. A survey with 48 engineers produced 169 prompts for different assemblies. Results show that prompts are mostly written as bullet points with an average of three and up to seven requirements. The engineers describe assemblies mainly through implicit functional descriptions and geometric or physical parameters. These findings form an empirical basis for developing generative AI-driven, prompt-based systems to foster design reuse.

This study evaluates the efficacy of various freely available Large Language Models (LLMs) in conducting semi-automated purpose-oriented technology searches to support design activities as well as Technology Intelligence for innovation management, using a systematic manual search as a baseline for comparison. The case to run the comparison focuses on identifying water purification technologies suitable for mobile systems. The results show that LLMs can target more technologies than human-based searches, reducing time demands and providing wider entry points for additional technology analysis.

This study investigated information retrieval of preprint records in the context of evidence synthesis work and compared 12 sources used to discover preprints. Identification of grey literature is often required or recommended in evidence synthesis guidance, and preprints are categorized as grey literature. The purpose of this work is to inform how and where to search for preprints to maximize coverage (through exploration of preprint server across aggregators and databases) while balancing search efficiency. Authors selected aggregators and databases hosting two or more preprint servers and then tested search functionality and extracted characteristics and features. Authors analyzed and compared the selected sources, tabulated the number of essential features, and created comparison tables reflecting database and aggregator features. The study protocol was registered in Open Science Framework registries. Preprint aggregators and databases differ in their content coverage, and their ability to design a comprehensive and reproducible search strategy. Limitations such as character or word limits for queries, limited advanced search operators, and missing export functionality affect the usability of aggregators for evidence synthesis searches. Ongoing updates to search interfaces and functionality and differing approaches to versioning make it challenging to study discovery of preprints across sources. The recommendations and scenarios in this article will assist searchers engaged in evidence synthesis to make informed decisions about where to search for preprints.

Evidence synthesis findings hinge upon well-designed, effective search strategies. When developing these strategies, evidence synthesis teams make multiple decisions (e.g., selecting information sources, developing search string architecture, and picking supplementary search methods) that directly affect the breadth of discovered evidence and thus evidence synthesis outcomes. Despite the number of decisions required when developing search strategies, limited guidance exists to inform these decisions using a data-driven approach. To help address this gap, we developed CiteSource, an R package and accompanying Shiny application, that supports data-driven search strategy development and reporting. CiteSource allows users to assign and retain metadata across three custom fields: source, label, and string to indicate where the records were found, what method or string was used to find them, and whether they were included after screening. CiteSource allows users to visually map the overlap between sets of records, create data summaries of citation records, and export citation records with the newly assigned metadata. CiteSource’s analysis and visualization outputs can be harnessed for a variety of use cases, such as optimizing literature source selection, honing and understanding the effectiveness of search strings, and evaluating the impacts of literature sources and supplementary search methods. Overall, CiteSource provides a tool for evidence synthesizers to make informed data-driven decisions that boost the efficiency, rigor, and transparency of search strategies and associated reporting.

The exploration and retrieval of information from large, unstructured document collections remain challenging. Unsupervised techniques, such as clustering and topic modeling, provide only a coarse overview of thematic structure, while traditional keyword searches often require extensive manual effort. Recent advances in large language models and retrieval-augmented generation (RAG) introduce new opportunities by enabling focused retrieval of relevant documents or chunks tailored to a user’s query. This allows for dynamic, chat-like interactions that streamline exploration and improve access to pertinent information. This article introduces Topic-RAG, a chat engine that integrates topic modeling with RAG to support interactive and exploratory document retrieval. Topic-RAG uses BERTopic to identify the most relevant topics for a given query and restricts retrieval to documents or chunks within those topics. This targeted strategy enhances retrieval relevance by narrowing the search space to thematically aligned content. We utilize the pipeline on 4,711 articles related to nuclear energy from the Impresso historical Swiss newspaper corpus. Our experimental results demonstrate that Topic-RAG outperforms a baseline RAG architecture that does not incorporate topic modeling, as measured by widely recognized metrics, such as BERTScore (including Precision, Recall and F1), ROUGE and UniEval. Topic-RAG also achieves improvements in computational efficiency for both single and batch query processing. In addition, we performed a qualitative analysis in collaboration with domain experts, who assessed the system’s effectiveness in supporting historically grounded research. Although our evaluation is focused on historical newspaper articles, the proposed approach more generally integrates topic information to enhance retrieval performance within a transparent and user-configurable pipeline effectively. It supports the targeted retrieval of contextually rich and semantically relevant content while also allowing users to adjust key parameters such as the number of documents retrieved. This flexibility provides greater control and adaptability to meet diverse research needs in historical inquiry, literary analysis and cultural studies. Due to copyright restrictions, the raw data cannot be publicly shared. Data access instructions are provided in the repository, and the replication code is available on GitHub: https://github.com/KeerthanaMurugaraj/Topic-RAG-for-Historical-Newspapers.

We present Digital Collections Explorer, a web-based, open-source exploratory search platform that leverages Contrastive Language-Image Pre-training for enhanced visual discovery of digital collections. Our Digital Collections Explorer can be installed locally and configured to run on a visual collection of interest on disk in just a few steps. Building upon recent advances in multimodal search techniques, our interface enables natural language queries and reverse image searches over digital collections with visual features. This article describes the system’s architecture, implementation and application to various cultural heritage collections, demonstrating its potential for democratizing access to digital archives, especially those with impoverished metadata. We present case studies with maps, photographs and PDFs extracted from web archives in order to demonstrate the flexibility of the Digital Collections Explorer, as well as its ease of use. We demonstrate that the Digital Collections Explorer scales to hundreds of thousands of images on a MacBook Pro with an M4 chip. Lastly, we host a public demo of Digital Collections Explorer.

Language is a powerful tool in legal research, but its influence is often underestimated. From the diplomatic fallout of the Ems Dispatch, to the varied terminology used to describe a person bringing a claim, in this article Holly Mottram examines how subtle variations in terminology have significantly altered global events and have a day-to-day impact on legal research outcomes. Several practical strategies are proposed to enhance research accuracy– focused contextual questioning, taking time at the beginning of a research task for keyword planning, and careful usage of artificial intelligence (AI) to assist the process. Ultimately, this paper argues that legal information professionals must remain vigilant and intentional in their language use if they wish to meet the needs of the requestor, and that their practices should evolve and adapt to not only account for changes in language, but changes in technology. Words matter– not just in theory, but in every day legal research.

The rise of GenAI (generative AI) tools such as ChatGPT has transformed the research environment, yet most legal researchers remain untrained in the theory, mechanics and epistemic structure of such systems. The public itself was introduced to GenAI through Generative Pre-Trained Transformer tools such as ChatGPT and Claude. Although AI is a decades-old academic discipline, it is now rapidly expanding, and LLM-based AI tools (called Legal Research AI Tools, or LRATs hereinafter, such as Lexis+ AI) sit at AI’s cutting edge within legal research. These LRATs rely on non-legal theoretical informational concepts and technologies to function. Legal researchers often struggle to understand how AI-enabled tools function, which makes effective/reliable use of them more difficult. Without proper orientation, legal professionals risk using LRATs with misplaced confidence and insufficient clarity, the implications of which will be addressed in a future article. This article, written by Ryan Marcotte, Reference, Instruction, & Scholarship law librarian at DePaul University’s College of Law in Chicago, Illinois, defines and explains AI-assisted legal research (AIALR) as a third phase of research logic following the traditional book-based legal research (BLR) and computer-assisted legal research (CALR) phases. It also introduces a definition of AI tailored for legal research, outlines key conceptual structures underpinning LRATs, and explains how they interpret human input. From this grounding, this article offers two frameworks: (1) the Five Ps Research Plan and (2) the four prompt engineering methodologies of Retrieval Augmented Generation, Few-Shot Prompting, Chain-of-Thought/Chain-of-Logic, and Prompt Chaining. Together, these frameworks equip legal researchers with the understanding and skills to plan, shape, and evaluate their research interactions with LRATs in the age of GenAI.

Systematic searches of published literature are a vital component of systematic reviews. When search strings are not “sensitive,” they may miss many relevant studies limiting, or even biasing, the range of evidence available for synthesis. Concerningly, conducting and reporting evaluations (validations) of the sensitivity of the used search strings is rare, according to our survey of published systematic reviews and protocols. Potential reasons may involve a lack of familiarity or inaccessibility of complex sensitivity evaluation approaches. We first clarify the main concepts and principles of search string evaluation. We then present a simple procedure for estimating a relative recall of a search string. It is based on a pre-defined set of “benchmark” publications. The relative recall, that is, the sensitivity of the search string, is the retrieval overlap between the evaluated search string and a search string that captures only the benchmark publications. If there is little overlap (i.e., low recall or sensitivity), the evaluated search string should be improved to ensure that most of the relevant literature can be captured. The presented benchmarking approach can be applied to one or more online databases or search platforms. It is illustrated by five accessible, hands-on tutorials for commonly used online literature sources. Overall, our work provides an assessment of the current state of search string evaluations in published systematic reviews and protocols. It also paves the way to improve evaluation and reporting practices to make evidence synthesis more transparent and robust.

We propose an unsupervised, corpus-independent method to extract keywords from a single text. It is based on the spatial distribution of words and the response of this distribution to a random permutation of words. Our method has three advantages over existing unsupervised methods (such as YAKE). First, it is significantly more effective at extracting keywords from long texts in terms of precision and recall. Second, it allows inference of two types of keywords: local and global. Third, it extracts basic topics from texts. Additionally, our method is language-independent and applies to short texts. The results are obtained via human annotators with previous knowledge of texts from our database of classical literary works. The agreement between annotators is moderate to substantial. Our results are supported via human-independent arguments based on the average length of extracted content words and on the average number of nouns in extracted words. We discuss relations of keywords with higher-order textual features and reveal a connection between keywords and chapter divisions.

Decompounding is an essential preprocessing step in text-processing tasks such as machine translation, speech recognition, and information retrieval (IR). Here, the IR issues are explored from five viewpoints. (A) Does word decompounding impact the Indian language IR? If yes, to what extent? (B) Can corpus-based decompounding models be used in the Indian language IR? If yes, how? (C) Can machine learning and deep learning-based decompounding models be applied in the Indian language IR? If yes, how? (D) Among the different decompounding models (corpus-based, hybrid machine learning-based, and deep learning-based), which provides the best effectiveness in the IR domain? (E) Among the different IR models, which provides the best effectiveness from the IR perspective? This study proposes different corpus-based, hybrid machine learning-based, and deep learning-based decompounding models in Indian languages (Marathi, Hindi, and Sanskrit). Moreover, we evaluate the effectiveness of each activity from an IR perspective only. It is observed that the different decompounding models improve IR effectiveness. The deep learning-based decompounding models outperform the corpus-based and hybrid machine learning-based models in Indian language IR. Among the different deep learning-based models, the Bi-LSTM-A model performs best and improves mean average precision (MAP) by 28.02% in Marathi. Similarly, the Bi-RNN-A model improves MAP by 18.18% and 6.1% in Hindi and Sanskrit, respectively. Among the retrieval models, the In_expC2 model outperforms others in Marathi and Hindi, and the BB2 model outperforms others in Sanskrit.

The complexity of process plants and the growing demand for digitalization require efficient and accurate information retrieval throughout the lifecycle phases of a process plant. This paper discusses the concept of instantiation and introduces a method for identifying and multiplying required information in plant engineering using scalable so-called Instantiation Blocks linked to the Bill of Material. Core functionality, an ontology graph and a user interface based on Python and React are developed to demonstrate the implementation of the framework and validate its effectiveness in practice.

Taxonomies are key to creating certainty in language across the legal landscape. In this article Alice Laird and Katy Snell of Howard Kennedy examine why taxonomies are still important in the age of AI. They also discuss how they have built on their expertise on taxonomies for the benefit of their firm, and how they have become involved with a cross firm project called noslegal.

This article is based on a course on how to use Moys classification scheme,1 delivered by Helen Garner and Felicity Staveley-Taylor on behalf of the British and Irish Association of Law Librarians (BIALL) in November 2022. The article, which is also written by Helen and Felicity, provides guidance on how to use Moys classification, explaining the features that enable the scheme to be expanded to accommodate new subject areas. The article also explains some of the features which ensure the scheme remains relevant to legal libraries today. Sections from the classification scheme, as published in the fifth edition, appear in the article text. In addition, any references to page numbers are to the fifth edition.

Latent semantic analysis (LSA) and correspondence analysis (CA) are two techniques that use a singular value decomposition for dimensionality reduction. LSA has been extensively used to obtain low-dimensional representations that capture relationships among documents and terms. In this article, we present a theoretical analysis and comparison of the two techniques in the context of document-term matrices. We show that CA has some attractive properties as compared to LSA, for instance that effects of margins, that is, sums of row elements and column elements, arising from differing document lengths and term frequencies are effectively eliminated so that the CA solution is optimally suited to focus on relationships among documents and terms. A unifying framework is proposed that includes both CA and LSA as special cases. We empirically compare CA to various LSA-based methods on text categorization in English and authorship attribution on historical Dutch texts and find that CA performs significantly better. We also apply CA to a long-standing question regarding the authorship of the Dutch national anthem Wilhelmus and provide further support that it can be attributed to the author Datheen, among several contenders.

Web search is an experience that naturally lends itself to recommendations, including query suggestions and related entities. In this article, we propose to recommend specific tasks to users, based on their search queries, such as planning a holiday trip or organizing a party. Specifically, we introduce the problem of query-based task recommendation and develop methods that combine well-established term-based ranking techniques with continuous semantic representations, including sentence representations from several transformer-based models. Using a purpose-built test collection, we find that our method is able to significantly outperform a strong text-based baseline. Further, we extend our approach to using a set of queries that all share the same underlying task, referred to as search mission, as input. The study is rounded off with a detailed feature and query analysis.