Information Retrieval Research Articles

Enhancing legal research through knowledge-infused information retrieval for Vietnamese labor law

<p>The role of intelligent information retrieval systems in legal research optimization has become increasingly recognized. There are many methods for exhibiting advance mentsin the proficient retrieval of legal documents. However, those methods fail to tackle the specific challenges encountered in real-world labor law searches. This research breaks new ground in Vietnamese labor law retrieval by leveraging a comprehensive dataset of 300,000 documents a cross diverse cat egories (20 document types and 27 legal fields) to train and evaluate retrieval models specifically designed for Vietnamese labor law. Unlike previous approaches, this work goes beyond simple information retrieval. It also constructs question & answer (Q&A) dataset specifically tailored to this legal domain. Be sides, this study introduces a novel approach of in corporating a legal ontology built from the data set itself. This knowledge in fusion significantly improves retrieval performance across legal search tasks, as demon strated through rigorous experimentation. These advancements empower intelligent systems to grasp the intricate semantic nuances of Vietnamese labor law.</p>

Design and implementation of EventsKG for situational monitoring and security intelligence in India: An open-source intelligence gathering approach

This paper presents a method to construct and implement an Events Knowledge Graph (EventsKG) for security-related open-source intelligence gathering, focusing on event exploration for situation monitoring in India. The EventsKG is designed to process news articles, extract events of national security significance, and represent them in a consistent and intuitive manner. This method utilizes state-of-the-art natural language understanding techniques and the capabilities of graph databases to extract and organize events. A domain-specific ontology is created for effective storage and retrieval. In addition, we provide a user-friendly dashboard for querying and a complete visualization of events across India. The effectiveness of the EventsKG is assessed through a human evaluation of the information retrieval quality. Our approach contributes to rapid data availability and decision-making through a comprehensive understanding of events, including local events, from every part of India in just a few clicks. The system is evaluated against a manually annotated dataset and by involving human evaluators through a feedback survey, and it has shown good retrieval accuracy. The EventsKG can also be used for other applications such as threat intelligence, incident response, and situational awareness.

Enhancing managerial decisions through strategic intelligence: The contribution of advanced information retrieval systems

This study explores the comparative impact of classic and advanced information retrieval sys- tems (IRS) on strategic intelligence and decision-making quality within organizations. Classic IRS, rooted in keyword-based searches and basic indexing, have supported decision-making by providing fast access to relevant data. However, their limitations in contextual depth, adaptabil- ity, and capacity to handle complex, unstructured information often restrict their effectiveness in today’s dynamic business environments. Advanced IRS, on the other hand, utilize techniques such as natural language processing, machine learning, and semantic analysis to deliver richer, contextually relevant insights. These systems enable a more comprehensive understanding of complex information landscapes, aligning with strategic goals and supporting proactive decision- making. The paper’s analysis highlights that while advanced IRS offer substantial advantages in data precision, strategic alignment, and responsiveness, they also entail higher costs and tech- nical requirements. The findings provide actionable insights for organizations in selecting and implementing the most suitable IRS to enhance decision quality, considering factors like orga- nizational goals, resources, and ethical considerations. This research contributes to the body of knowledge on strategic intelligence by examining the evolution of IRS and their implications for organizational success.

Emerging Trends in Real-time Recommendation Systems: A Deep Dive into Multi-behavior Streaming Processing and Recommendation for E-commerce Platforms

This paper aims to assess the effectiveness of recommendation systems, focusing on multi-behavior streaming processing to enhance accuracy. It studies recommendation system performance using AI and data science, focusing on user behaviour, algorithm refinement, and satisfaction. E-commerce, streaming, and social media datasets with 93 anonymous participants were employed in experiments. These files from 93 anonymized users show typical internet use. Data anonymization and strict data management ensured anonymity. These databases track clicks, views, purchases, and ratings for empirical research and model evaluation. Collaborative filtering, matrix factorization, and TensorFlow/Keras train and assess application-specific recommendation models. Multi-behavior streaming processing and recommendation accounts assess each method's pros and downsides, system correctness, efficacy, and user involvement. The outcome compares domain-wide recommendation system precision, recall, NDCG, and conversion rate. Multi-behavior streaming processing adapts to user preferences and interactions to improve model accuracy and adaptability. Multi-behavior streaming processing improved model accuracy and flexibility by reacting to user inputs and choices. With error margins for all significant metrics, statistical significance was confirmed. The findings suggest that recommendation systems with real-time adaptation and multi-behavior streaming processing can improve user satisfaction and engagement in the changing digital landscape. It encourages algorithm advancement, model interpretation, user-centric evaluation, and ethics to improve information retrieval and personalisation. The study concluded that algorithm refinement, transparent model interpretation, user-centric evaluation, and ethical problems including data protection and bias mitigation increase information retrieval and personalisation. For durable and flexible recommendation systems, research should improve multi-behavior processing and sectoral applications.

Revolutionizing library systems with advanced automation: A blueprint for efficiency in academic resource management

The advent of advanced automation technologies has the potential to revolutionize library systems, particularly within academic institutions, where effective resource management is essential. This paper outlines a comprehensive blueprint for integrating automation into library operations to enhance efficiency, accessibility, and user engagement. Key technologies discussed include Radio Frequency Identification (RFID), Artificial Intelligence (AI), and Machine Learning (ML), which streamline processes such as cataloging, circulation, and inventory management. The implementation of RFID facilitates self-service checkouts and real-time inventory tracking, significantly reducing the time spent on manual tasks, thereby allowing library staff to concentrate on enhancing user experiences and curating resources strategically. Furthermore, AI-driven chatbots provide personalized recommendations, improving user satisfaction and ensuring that patrons receive tailored support. This blueprint emphasizes the role of automated digital repositories and intelligent content indexing systems, which accelerate cataloging and ensure timely access to scholarly materials. By automating information retrieval processes, libraries can reduce wait times and improve the overall accessibility of resources. Data analytics are also pivotal, enabling libraries to monitor usage patterns, optimize resource allocation, and forecast future demands, ensuring alignment with academic priorities. Moreover, the paper addresses challenges related to automation implementation, including financial constraints, data privacy concerns, and staff training requirements, proposing solutions such as gradual implementation and interdepartmental collaboration. Ultimately, the transition to advanced automation not only enhances operational efficiency but also boosts academic productivity by making resources more accessible and user-centered. This strategic move toward a digital-first library environment signifies a profound transformation in academic libraries, promoting an agile approach to resource management. As institutions increasingly adopt these technologies, they position themselves at the forefront of educational innovation, effectively integrating academic resources into the digital learning landscape.

An Automated Daily News Reports Generating Application Involving Keyword-Based News Scraping, Summarization, and Sentimental Analysis Leveraging NLP Models

In the era of information overload, obtaining relevant, concise, and sentiment-analyzed news content is essential for effective decision-making. This paper introduces an automated daily news reporting system that streamlines the process of collecting, summarizing, and analyzing the sentiment of news articles fetched based on the user's keyword. By leveraging stateof-the-art Natural Language Processing (NLP) models like GPT-3.5 for two-level summarization and BERTweet for sentiment analysis, the system provides users with concise, sentiment-labeled reports, enhancing their understanding of news trends and emotional tone. The architecture integrates data scraping, text extraction, and sentiment classification within a cloud-based Python microservice, supported by Flask. The system incorporates user localization options, allowing users to customize news retrieval by region and time preferences. Finalized reports are formatted into HTML and delivered directly to authenticated user emails through Gmail API, ensuring seamless and secure distribution. This research underscores the significance of automated news summarization and sentiment analysis in modern information retrieval. It provides a scalable and personalized solution that enables real-time synthesis of large volumes of news content, making it accessible and relevant for diverse audiences worldwide.

An Ecological Momentary Assessment and Intervention Tool for Memory in Chronic Traumatic Brain Injury: Development and Usability of Memory Ecological Momentary Intervention.

Memory and learning deficits are among the most impactful and longest-lasting symptoms experienced by people with chronic traumatic brain injury (TBI). Despite the persistence of post-TBI memory deficits and their implications for community reintegration, memory rehabilitation is restricted to short-term care within structured therapy sessions. Technology shows promise to extend memory rehabilitation into daily life and to increase the number and contextual diversity of learning opportunities. Ecological momentary assessment and intervention frameworks leverage mobile phone technology to assess and support individuals' behaviors across contexts and have shown benefits in other chronic conditions. However, few studies have used regular outreach via text messaging for adults with chronic TBI, and none have done so to assess and support memory. This study aimed to develop and test the usability of memory ecological momentary intervention (MEMI), a text message-based assessment and intervention tool for memory in daily life. MEMI is designed to introduce new information, cue retrieval of the information, and assess learning across time and contexts. We tested MEMI via an iterative, user-centered design process to ready it for a future trial. We developed MEMI by leveraging automated text messages for prompts using a REDCap (Research Electronic Data Capture)/Twilio interface linking to the Gorilla web-based behavioral experimental platform. We recruited 14 adults with chronic, moderate-severe TBI from the Vanderbilt Brain Injury Patient Registry to participate in 3 rounds of usability testing: one round of ThinkAloud sessions using the platform and providing real-time feedback to an experimenter (n=4) and 2 rounds of real-world usability testing in which participants used MEMI in their daily lives for a week and provided feedback (n=5/round). We analyzed engagement and quantitative and qualitative user feedback to assess MEMI's usability and acceptability. Participants were highly engaged with MEMI, completing an average of 11.8 out of 12 (98%) possible sessions. They rated MEMI as highly usable, with scores on the System Usability Scale across all rounds equivalent to an A+ on a standardized scale. In semistructured interviews, they stated that MEMI was simple and easy to use, that daily retrieval sessions were not burdensome, and that they perceived MEMI as helpful for memory. We identified a few small issues (eg, instruction wording) and made improvements between usability testing rounds. Testing MEMI with adults with chronic TBI revealed that this technology is highly usable and favorably rated for this population. We incorporated feedback regarding users' preferences and plan to test the efficacy of this tool in a future clinical trial.

Movie Recommendation System Based on Collaborative Filtering Network

Abstract. In the era of big data, personalized recommendation systems have become crucial for enhancing user experience and improving information retrieval efficiency, especially in the movie recommendation domain. This study proposes a method based on Collaborative Filtering Network (CFN), utilizing deep learning techniques to construct an efficient and accurate movie recommendation system. We evaluated the model's effectiveness using the MovieLens dataset. The experimental results demonstrate that the proposed CFN model performs well across multiple metrics, including Hit Ratio, providing new insights for research in the recommendation system field.

Enhancing retrieval performance of embedding models via fine-tuning on synthetic data in RAG chatbot for Vietnamese military science domain

Retrieval-Augmented Generation (RAG) is a technology that combines information retrieval with large language models, enabling chatbots to provide accurate answers by querying relevant documents from a data repository before generating responses. While RAG chatbot has demonstrated effectiveness in many applications, there are still limitations in specialized Vietnamese data domains, particularly in the military science field. To address this challenge, this paper proposes a framework for fine-tuning embedding models using synthetic datasets generated by ChatGPT to enhance retrieval performance in a Q&A application focused on the history of the Institute of Information Technology (IoIT). Our approach evaluates 11 popular embedding models and shows a significant average improvement of 18.15% in the MAP@K metric. The resulting IoIT history Q&A chatbot, developed with fine-tuned embedding models and the Vietnamese language model Vistral-7B, outperforms chatbots utilizing OpenAI's embedding models and ChatGPT. These findings highlight the potential of RAG chatbot technology for advancing information retrieval applications in specialized fields like military science.

Application of Prompt Engineering Techniques to Optimize Information Retrieval in the Metaverse

Prompt engineering techniques are instructions that enable large language models (LLMs) to solve real-world problems more effectively. These techniques enhance the capabilities of LLMs to generate accurate and efficient responses. Our study examines the challenge of acquiring comprehensive and efficient information in the metaverse through the application of various prompt engineering techniques. The main objective is to improve the accuracy and effectiveness of metaverse-related responses by leveraging LLM capabilities. In this study, 100 questions were generated using GPT, GEMINI, QWEN, and MISTRAL language models focusing on the metaverse. Our experiments indicated that responses often included unrelated information, highlighting the need for prompt engineering techniques. We applied knowledge-based, rule-based, few-shot, and template-based prompt engineering techniques to refine the responses. The performance of GPT, GEMINI, QWEN, and MISTRAL models were evaluated based on criteria including accuracy, timeliness, comprehensiveness, and consistency. Our findings reveal that prompt engineering techniques significantly enhance the efficacy of LLMs in providing improved information retrieval and response generation, aiding users in efficiently acquiring information in complex environments like the metaverse.

PICOT questions and search strategies formulation: A novel approach using artificial intelligence automation.

The aim of this study was to evaluate and compare artificial intelligence (AI)-based large language models (LLMs) (ChatGPT-3.5, Bing, and Bard) with human-based formulations in generating relevant clinical queries, using comprehensive methodological evaluations. To interact with the major LLMs ChatGPT-3.5, Bing Chat, and Google Bard, scripts and prompts were designed to formulate PICOT (population, intervention, comparison, outcome, time) clinical questions and search strategies. Quality of the LLMs responses was assessed using a descriptive approach and independent assessment by two researchers. To determine the number of hits, PubMed, Web of Science, Cochrane Library, and CINAHL Ultimate search results were imported separately, without search restrictions, with the search strings generated by the three LLMs and an additional one by the expert. Hits from one of the scenarios were also exported for relevance evaluation. The use of a single scenario was chosen to provide a focused analysis. Cronbach's alpha and intraclass correlation coefficient (ICC) were also calculated. In five different scenarios, ChatGPT-3.5 generated 11,859 hits, Bing 1,376,854, Bard 16,583, and an expert 5919 hits. We then used the first scenario to assess the relevance of the obtained results. The human expert search approach resulted in 65.22% (56/105) relevant articles. Bing was the most accurate AI-based LLM with 70.79% (63/89), followed by ChatGPT-3.5 with 21.05% (12/45), and Bard with 13.29% (42/316) relevant hits. Based on the assessment of two evaluators, ChatGPT-3.5 received the highest score (M = 48.50; SD = 0.71). Results showed a high level of agreement between the two evaluators. Although ChatGPT-3.5 showed a lower percentage of relevant hits compared to Bing, this reflects the nuanced evaluation criteria, where the subjective evaluation prioritized contextual accuracy and quality over mere relevance. This study provides valuable insights into the ability of LLMs to formulate PICOT clinical questions and search strategies. AI-based LLMs, such as ChatGPT-3.5, demonstrate significant potential for augmenting clinical workflows, improving clinical query development, and supporting search strategies. However, the findings also highlight limitations that necessitate further refinement and continued human oversight. AI could assist nurses in formulating PICOT clinical questions and search strategies. AI-based LLMs offer valuable support to healthcare professionals by improving the structure of clinical questions and enhancing search strategies, thereby significantly increasing the efficiency of information retrieval.

Survey on Focused Web Crawling Approaches for Ayurvedic Plant Information Retrieval

The Ayurvedic medical system is heavily reliant on medicinal plants, demanding correct information retrieval from the web. This study examines specific web crawling strategies for collecting useful information about Ayurvedic botanicals, with a focus on deep learning methodologies. Crawlers optimized with machine learning models retrieve domain-specific content while filtering out unnecessary data. The paper looks at approaches such as the TRES framework, which is a reinforcement learning-based crawler that discretizes vast state and action spaces in order to effectively choose ideal URLs. Furthermore, convolutional neural networks (CNN) and natural language processing (NLP) have been used in crawlers to improve categorization, as demonstrated by successful Turkish language processing applications. The paper "Learning to Crawl: Comparing Classification Schemes" conducts a comparative comparison of old rule-based approaches and newer deep learning classifiers, demonstrating the latter's superiority. In addition, a Naive Bayes classifier is employed in an Ayurvedic plant-focused crawler, which employs query expansion via a carefully curated thesaurus to improve relevancy in retrieved web pages. This poll emphasizes the need for more efficient, adaptive, and focused crawlers powered by deep learning to progress Ayurvedic research.

Quantitative Evaluation of Post-Tillage Soil Structure Based on Close-Range Photogrammetry

Quantitative Evaluation of Post-Tillage Soil Structure Based on Close-Range Photogrammetry

Assessment of Metaliteracy Competencies Among Library Professionals in Indian Institutes of Technology

The digital revolution has reshaped academic libraries, requiring new skills from library professionals. This study explores how library professionals at Indian Institutes of Technology (IITs) are adapting to this change through their metaliteracy skills. By surveying 144 library professionals across IITs, we uncovered a complex process of digital adaptation and professional growth. Our findings reveal that most professionals are confidently entering the digital era, with three-quarters showing proficiency in basic digital tools. However, beneath this digital fluency lies a more intricate picture. While many excel in traditional tasks like database management and information retrieval − 65% reported high proficiency – there is notable reluctance when engaging with emerging technologies and cybersecurity challenges. Surprisingly, gender significantly influenced how professionals approached information evaluation and synthesis. Experience, though important for many metaliteracy skills, seemed less relevant in addressing modern concerns such as privacy protection and detecting misinformation. One of the most revealing findings is the gap between competence and teaching ability: although many professionals possess strong technical skills, only 31.5% feel confident in teaching these skills to others. This highlights the urgent need for targeted professional development that considers both gender dynamics and varying experience levels. By shedding light on these patterns, our study offers a pathway to reinforce the digital infrastructure of India’s leading technical institutions, ensuring library professionals can guide future researchers through an increasingly complex information landscape. Our findings not only enhance our understanding of metaliteracy in academic libraries but also provide practical insights for designing training programs to address these gaps. Ultimately, this work contributes to the broader discussion on digital transformation in academic libraries and the evolving role of library professionals in the digital age.

A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions

The emergence of large language models (LLMs) has marked a significant breakthrough in natural language processing (NLP), fueling a paradigm shift in information acquisition. Nevertheless, LLMs are prone to hallucination, generating plausible yet nonfactual content. This phenomenon raises significant concerns over the reliability of LLMs in real-world information retrieval (IR) systems and has attracted intensive research to detect and mitigate such hallucinations. Given the open-ended general-purpose attributes inherent to LLMs, LLM hallucinations present distinct challenges that diverge from prior task-specific models. This divergence highlights the urgency for a nuanced understanding and comprehensive overview of recent advances in LLM hallucinations. In this survey, we begin with an innovative taxonomy of hallucination in the era of LLM and then delve into the factors contributing to hallucinations. Subsequently, we present a thorough overview of hallucination detection methods and benchmarks. Our discussion then transfers to representative methodologies for mitigating LLM hallucinations. Additionally, we delve into the current limitations faced by retrieval-augmented LLMs in combating hallucinations, offering insights for developing more robust IR systems. Finally, we highlight the promising research directions on LLM hallucinations, including hallucination in large vision-language models and understanding of knowledge boundaries in LLM hallucinations.

A Noise-Oriented and Redundancy-Aware Instance Selection Framework

Fine-tuning transformer-based deep learning models is currently at the forefront of natural language processing (NLP) and information retrieval (IR) tasks. However, fine-tuning these transformers for specific tasks, especially when dealing with ever-expanding volumes of data, constant retraining requirements, and budget constraints, can be computationally and financially costly, requiring substantial energy consumption and contributing to carbon dioxide emissions. This article focuses on advancing the state-of-the-art (SOTA) on instance selection (IS) – a range of document filtering techniques designed to select the most representative documents for the sake of training. The objective is to either maintain or enhance classification effectiveness while reducing the overall training (fine-tuning) total processing time. In our prior research, we introduced the E2SC framework, a redundancy-oriented IS method focused on transformers and large datasets – currently the state-of-the-art in IS. Nonetheless, important research questions remained unanswered in our previous work, mostly due to E2SC's sole emphasis on redundancy. In this article, we take our research a step further by proposing biO-IS – an extended bi - ob jective i nstance s election solution, a novel IS framework aimed at simultaneously removing redundant and noisy instances from the training. biO-IS estimates redundancy based on scalable, fast, and calibrated weak classifiers and captures noise with the support of a new entropy-based step. We also propose a novel iterative process to estimate near-optimum reduction rates for both steps. Our extended solution is able to reduce the training sets by 41% on average (up to 60%) while maintaining the effectiveness in all tested datasets, with speedup gains of 1.67 on average (up to 2.46x). No other baseline, not even our previous SOTA solution, was capable of achieving results with this level of quality, considering the tradeoff among training reduction, effectiveness, and speedup. To ensure reproducibility, our documentation, code, and datasets can be accessed on GitHub – https://github.com/waashk/bio-is .

Developing Semantic Textual Similarity for Guragigna Language Using Deep Learning Approach

Semantic Similarity is one of the highest levels of NLP. STS has significant advantages in NLP applications like information retrieval, information extraction, text summarization, data mining, machine translation, and other tasks. This research aims to present a deep learning approach for capturing semantic textual similarity (STS) in the Guragigna. The methodology involves collecting a Guragigna language corpus and preprocessing the text data and text representation is done using the Universal Sentence Encoder (USE), along with word embedding techniques including Word2Vec and GloVe and mean Square Error (MSE) is used to measure the performance. In the experimentation phase, models like LSTM, Bidirectional RNN, GRU, and Stacked RNN are trained and evaluated using different embedding techniques. The results demonstrate the efficacy of the developed models in capturing semantic textual similarity in the Guragigna language. Across different embedding techniques, including Word2Vec, GloVe, and USE, the Bidirectional RNN model with USE embedding achieves the lowest MSE of 0.0950 and the highest accuracy of 0.9244. GloVe and Word2Vec embedding also show competitive performance with slightly higher MSE and lower accuracy. The Universal Sentence Encoder consistently emerges as the top-performing embedding across all RNN architectures. The research results demonstrate the effectiveness of LSTM, GRU, Bi RNN, and Stacked RNN models in measuring semantic textual similarity in the Guragigna language.

Integrating a Virtual Assistant by Using the RAG Method and VERTEX AI Framework at Algebra University

The development and testing of a virtual assistant (VA) designed to enhance information retrieval and support in an academic environment are presented in this paper, with the Retrieval-Augmented Generation (RAG) approach being utilized alongside Google’s VERTEX AI Palm-2 model. A novel integration of RAG with contextual learning is introduced in this study, specifically for applications in university contact centers, where accuracy and relevance are considered paramount. The effectiveness of the VA was evaluated through user testing, focusing on two primary hypotheses: first, that the VA can achieve accurate interpretation and response to queries with context-based information, and second, that the VA minimizes potential harm from erroneous responses. In total, 187 participants were involved in the testing, and a diverse set of inquiries was utilized, resulting in 561 query–response interactions that were analyzed. It was shown that contextual data significantly reduced hallucinations and increased response accuracy, thereby underscoring the value of the RAG method in applications requiring high levels of specificity. Furthermore, the study provides empirical insights into the impact of AI-generated hallucinations and response inconsistencies, particularly about structured or procedural data. A framework for mitigating these challenges in future implementations is also offered. The scalability and adaptability of the RAG method in specialized academic contexts are demonstrated in this work, with broader implications for integrating AI-driven VAs across educational and professional domains being highlighted.

Enhancing Plant Species Retrieval in Flora Through Language Model Integration

Traditionally, textual data storage and retrieval systems were designed primarily for human reading, mainly relying on paper records. However, as information technology has advanced, computerized searches have become common. However, Boolean logic-based data retrieval systems often struggle to handle data's diversity and richness effectively. These systems rely on strict matching rules, which can lead to either too few or too many results. For example, when searching for plant species descriptions, a query like "circle" AND "ellipse" may exclude relevant records that describe these traits using slightly different terms (e.g., "round" or "oval"). Conversely, broader queries like "oblong" may return an overwhelming number of irrelevant results. This rigidity limits the system's ability to adapt to the nuanced and varied ways users describe data. With the advent of advanced semantic models such as SBERT (Sentence-Bidirectional Encoder Representations from Transformers) (Reimers and Gurevych 2019), we can now delve deeper into the semantic relationships within textual data. Unlike general-purpose large language models, SBERT is specifically designed for efficient semantic similarity computation. In plant taxonomy, records in Flora, such as Flora of Taiwan or Flora of China, play a crucial role in understanding plant diversity in specific regions. These records provide critical information on plant growth environments, morphological characteristics, and economic values. Our research aims to enhance the efficiency of retrieving plant data using language models. Specifically, we transform textual descriptions from Flora and user queries into vector representations (Fig. 2) and calculate their cosine similarity to determine the relevance between user inputs and species records. Cosine similarity, a metric commonly used in text mining and information retrieval, quantifies the similarity between two vectors by measuring the cosine of the angle between them. The similarity score ranges from -1 (completely dissimilar) to 1 (identical), where higher scores indicate greater similarity. By applying this method, we can provide users with ranked scores of plant species related to their queries (Fig. 1). This approach not only streamlines data retrieval but also introduces new perspectives for botanical research and data management, fostering a more efficient exploration of plant diversity. Our results demonstrate the potential of language models to facilitate biodiversity research and data management, especially in retrieving plant taxonomy information. Our approach provides a novel tool for future biodiversity data analysis and retrieval, thereby contributing to the progress of biodiversity conservation.

“I wish I could use any language as it comes to mind”: User experience in digital platforms in the context of multilingual personal information management

AbstractIn today's linguistically diverse world, managing personal information across multiple languages presents a challenge. This study engaged 16 multilingual participants to explore their user experience in the context of multilingual personal information management (MPIM), with a focus on inclusivity, universality, and equity. Addressing two main questions, the study explores the challenges users face on digital platforms in MPIM contexts and their ideal platform features. Findings highlight key issues in MPIM platform design, including unsupported languages and integration of visual aesthetics. We also identify user preferences for ideal platform features, such as language flexibility and efficient information retrieval. The study suggests the need for more inclusive, universal, and equitable platform designs that cater to the specific requirements of multilingual users. Ultimately, this study underscores the critical need for improved MPIM support and emphasizes the significance of continued exploration in this area, establishing it as a vital field of future research.