Crop phenology data extraction from research papers using a large language model

Interacting with Large Language Models (LLMs) via declarative queries is increasingly popular for tasks like question answering and data extraction, thanks to their ability to process vast unstructured data. However, LLMs often struggle with answering complex factual questions, exhibiting low precision and recall in the returned data. This challenge highlights that executing queries on LLMs remains a largely unexplored domain, where traditional data processing assumptions often fall short. Conventional query optimization, typically cost-driven, overlooks LLM-specific quality challenges such as contextual understanding. Just as new physical operators are designed to address the unique characteristics of LLMs, optimization must consider these quality challenges. Our results highlight that adhering strictly to conventional query optimization principles fails to generate the best plans in terms of result quality. To tackle this challenge, we present a novel approach to enhance SQL results by applying query optimization techniques specifically adapted for LLMs. We introduce a database system, GALOIS, that sits between the query and the LLM, effectively using the latter as a storage layer. We design alternative physical operators tailored for LLM-based query execution and adapt traditional optimization strategies to this novel context. For example, while pushing down operators in the query plan reduces execution cost (fewer calls to the model), it might complicate the call to the LLM and deteriorate result quality. Additionally, these models lack a traditional catalog for optimization, leading us to develop methods to dynamically gather such metadata during query execution. Our solution is compatible with any LLM and balances the trade-off between query result quality and execution cost. Experiments show up to 144% quality improvement over questions in Natural Language and 29% over direct SQL execution, highlighting the advantages of integrating database solutions with LLMs.

ObjectiveThrough this scoping review, we aim to explore and synthesize existing knowledge and evidence on the learning approaches for incorporating LLMs into healthcare education and public health research and learning spaces. Specifically, we will attempt to investigate methods for auditing prompts for accuracy, fairness, and effectiveness; tailoring prompts to improve task-specific accuracy and utility; and exploring how end-user feedback is used to refine and optimize LLM prompts over time. This review will provide a comprehensive understanding of how LLMs are being tailored and improved in these fields, contributing to the development of evidence-based strategies for their implementation. It will also identify areas for future research and innovation.IntroductionThe increasing integration of large language models (LLMs) into healthcare education and public health research and learning spaces, highlights their potential to revolutionize service delivery, decision-making, and ultimately patient care and outcomes. Despite these advancements, understanding how LLMs can be effectively tailored, audited, and refined for learning remains a critical area of inquiry. Key issues include, the accuracy of generated information, and their relevance to the medical and public health fields.Inclusion criteriaOur focus will be on studies addressing LLM applications in healthcare education and public health research and learning spaces, prompt engineering techniques, prompt auditing methods, and processes geared towards integrating user feedback. Articles that do not focus on healthcare or public health contexts and lack relevance to LLM learning approaches will be excluded.MethodsThe review is guided by the JBI methodology for scoping reviews complemented by updates from Levac et al. Databases including PubMed, Scopus, IEEE Xplore, and Web of Science will be searched for peer-reviewed articles, conference proceedings, and grey literature published in English and French from 2015 to 2025. Data extraction will include information on study characteristics, LLM models, prompt engineering strategies, auditing methodologies, and user feedback mechanisms. We will synthesize to identify trends, gaps, and best practices in leveraging LLMs to generate baseline data for auditing prompts that optimize AI learning and education needs in the healthcare and public health sector.

Identifying drilling risks for upcoming wells demands insights from offset wells. While some risks may lead to non-productive time (NPT), others remain latent within daily drilling reports (DDRs), which is crucial for comprehensive analysis. Manual extraction from DDRs is often time-consuming. In this paper, we systematically explore the methods to leverage the Large Language Models (LLMs) with enhanced workflows to automate insights extraction and improve risk identification accuracy. We compared LLMs customization approaches and state-of-the-art NLP models to validate LLMs efficiency in the drilling domain. We show that the adaptation of prompt optimization, Retrieval Augmented Generation (RAG) with the pre-trained LLMs before fine-tuning the model, already shows a significant improvement, achieving an accuracy ranging from 80-85%, with precision and recall surging from less than 50%, as observed from our benchmark oil and gas finetuned GPT-2 model (Marlot et al., 2023), to over 70% with our customized model. We addressed the challenge of imbalance training examples during the finetuning of the state-of-the-art GPT-2 model, which caused the underperformance of the benchmark model, particularly in addressing rare drilling event classes. This paper demonstrates LLMs able to improve the generalization and reliability of the imbalance drilling risks, with proper workflow enhancements. Subsequently, we also finetuned both on-premises LLMs (Llama2, Llama3, Mistral), and cloud LLM GPT-3.5 Turbo, which exhibits promising outcomes, achieving better performance to over 90% accuracy, and over 80% precision and recall, compared to the earlier approach using prompt and RAG. This paper contributes to advancing the application of LLMs in the oil and gas industry, for domain-specific tasks, addressing the common challenge of imbalance operation training data, and demonstrating our enhanced workflow outperforms both the benchmark finetuned GPT-2 model, pretrained GPT-4 model, and the finetuned GPT-3.5 Turbo.

Objective To evaluate and synthesise current applications of large language models (LLMs) in systematic reviews and meta-analyses (SRMAs), identify key limitations and propose an enhanced theoretical framework to improve the efficiency, scalability and reliability of evidence synthesis. Methods and analysis We conducted a narrative review of recent studies applying LLMs across key SRMA stages. A total of 21 publications were analysed for model type, task application, accuracy metrics and workflow impact. Building on this evidence base, we designed a comprehensive LLM-enhanced SRMA framework that categorises LLM roles as consultants and assistants, integrates human-in-the-loop strategies and uses retrieval-augmented generation (RAG) and agent-based architectures to address critical challenges including hallucinations, bias and workflow inefficiency. Results The reviewed literature demonstrated that LLMs can support various SRMA tasks with reported accuracy ranging from 61% to 99%, showing particular promise in literature screening and data extraction. Our proposed framework conceptualises modular integration of LLMs across all six SRMA stages, with LLMs serving as consultants for research question formulation and search strategy development and as assistants for task automation including abstract screening and structured data extraction. The framework incorporates RAG technology to reduce hallucinations by grounding outputs in retrieved literature and employs agent-based orchestration for complex analytical workflows. Theoretical analysis suggests potential for significant efficiency gains while maintaining methodological rigour through strategic human oversight. Conclusion LLMs offer substantial theoretical potential to transform evidence synthesis by improving efficiency, scalability and consistency across SRMA workflows. The proposed LLM-enhanced framework provides a systematic, theoretically grounded approach for integrating advanced artificial intelligence capabilities into existing SRMA methodologies while preserving essential human oversight and analytical integrity. Future empirical studies are needed to validate the framework’s practical effectiveness, establish implementation protocols and demonstrate real-world benefits in evidence-based medicine.

The article presents a methodology for designing a benchmark to assess numerical reasoning skills in Large Language Models (LLMs). In the context of LLMs, numerical reasoning is defined as a model’s ability to correctly interpret, process, and utilize numerical information in text, including understanding magnitudes and relations between numbers, performing arithmetic operations, and generating numerals accurately in its outputs. The proposed methodology is based on decomposing applied tasks and enables targeted evaluation of specific facets of numerical reasoning using tasks that involve numerals. Particular attention is paid to the representation of numbers in textual prompts to LLMs, as this factor directly affects the quality of the final output. The need for rigorous assessment of LLMs’ numerical reasoning stems from its critical role across a wide range of text-centric applications, including automated summarization, generation of analytical reports, extraction and interpretation of quantitative data, and conversational systems operating on financial, scientific, or technical information. Drawing on an analysis of state-of-the-art LLM evaluation approaches, core principles for constructing evaluation benchmarks are formulated with an emphasis on generality and real-world applicability. In accordance with the proposed methodology, the MUE (Math Understanding Evaluation) benchmark is introduced; it comprises five test suites, each designed to assess a distinct aspect of LLM numerical reasoning. A comparative evaluation of popular LLMs is conducted, leading models are identified, and the strengths and weaknesses of their numerical reasoning are characterized. The findings are intended to inform LLM developers in refining architectures and training strategies, and to guide end users and integrators in selecting an optimal model for applied projects.

IntroductionIn recent years, large language models (LLMs) have emerged as powerful tools in natural language processing, presenting diverse opportunities across various sectors. In this context, the Agency for Health Quality and Assessment of Catalonia (AQuAS) is actively investigating how LLMs can enhance the development of health technology assessment (HTA) reports.MethodsTo assess the potential of LLMs in the development of HTA reports, our initial step involved a comprehensive review of technical literature to understand the functionalities of existing LLM tools. This effort was followed by a systematic identification of specific HTA report development tasks that these models could potentially facilitate. We then rigorously evaluated the performance of these tools in executing the delineated tasks, with a focus on meticulously recording the applied prompts and areas of high and low effectiveness, alongside any encountered errors and identified risks.ResultsAmong a range of commercial tools, ChatGPT and Microsoft Copilot were selected for exploration due to their accessibility, ease of use, and versatility. Both tools demonstrated acceptable performance in certain tasks (e.g., data extraction), while their efficacy was notably lower in others (e.g., information search). Additionally, a range of risks requiring mitigation were identified (e.g., hallucination or authority bias). Consequently, we drafted a proposal for an internal guide with directives for the technical staff of the HTA unit on utilizing these two tools. Additionally, we constituted a working group.ConclusionsLLMs have emerged as promising tools in the field of HTA. Over the past months, AQuAS has been investigating the potential of these models to improve the HTA report development process, targeting enhanced efficiency and improved quality. This exploration has led to the identification of numerous opportunities and associated risks within this innovative application.

Large language models (LLMs) have demonstrated abilities to perform complex tasks in multiple domains, including mathematical and scientific reasoning. We demonstrate that with carefully designed prompts, LLMs can accurately carry out key calculations in research papers in theoretical physics. We focus on a broadly-used approximation method in quantum physics: the Hartree-Fock method, requiring an analytic multi-step calculation deriving approximate Hamiltonian and corresponding self-consistency equations. To carry out the calculations using LLMs, we design multi-step prompt templates that break down the analytic calculation into standardized steps with placeholders for problem-specific information. We evaluate GPT-4’s performance in executing the calculation for 15 papers from the past decade, demonstrating that, with the correction of intermediate steps, it can correctly derive the final Hartree-Fock Hamiltonian in 13 cases. Aggregating across all research papers, we find an average score of 87.5 (out of 100) on the execution of individual calculation steps. We further use LLMs to mitigate the two primary bottlenecks in this evaluation process: (i) extracting information from papers to fill in templates and (ii) automatic scoring of the calculation steps, demonstrating good results in both cases.

The emergence of large language models (LLMs) and the increasing prevalence of electronic health records (EHRs) present significant opportunities for advancing health care research and practice. However, research that compares and applies LLMs to extract key epilepsy-related information from unstructured medical free text is under-explored. This study fills this gap by comparing and applying different open-source LLMs and methods to extract epilepsy information from unstructured clinic letters, thereby optimizing EHRs as a resource for the benefit of epilepsy research. We also highlight some limitations of LLMs. Employing a dataset of 280 annotated clinic letters from King's College Hospital, we explored the efficacy of open-source LLMs (Llama and Mistral series) for extracting key epilepsy-related information, including epilepsy type, seizure type, current anti-seizure medications (ASMs), and associated symptoms. The study used various extraction methods, including direct extraction, summarized extraction, and contextualized extraction, complemented by role-prompting and few-shot prompting techniques. Performance was evaluated against a gold standard dataset, and was also compared to advanced fine-tuned models and human annotations. Llama 2 13b (a 13-billion-parameter LLM developed by Meta) demonstrated superior extraction capabilities across tasks by consistently outperforming other LLMs (F1 = .80 in epilepsy-type extraction, F1 = .76 in seizure-type extraction, and F1 = .90 in current ASMs extraction). Here, F1 score is a balanced metric indicating the model's accuracy in correctly identifying relevant information without excessive false positives. The study highlights the direct extraction showing consistent high performance. Comparative analysis showed that LLMs outperformed current approaches like MedCAT (Medical Concept Annotation Tool) in extracting epilepsy-related information (.2 higher in F1). The results affirm the potential of LLMs in medical information extraction relating to epilepsy, offering insights into leveraging these models for detailed and accurate data extraction from unstructured texts. The study underscores the importance of method selection in optimizing extraction performance and suggests a promising avenue for enhancing medical research and patient care through advanced natural language processing technologies.

Large Language Models (LLMs) have demonstrated powerful capabilities in the field of code generation, with a deep understanding of the semantics and functionality of code. Building websites is one of the most important tasks in software development, as it utilizes rich frontend displays and backend processing to achieve various service functions. It is one of the most widely used interactive software models. Although there have been some efforts in Web website generation, these efforts have been limited to the automation of generating Web pages. The advent of LLMs provides a new approach to Web site generation tasks. However, there is currently a lack of comprehensive evaluation of the generation performance of LLMs in this context, making it difficult to optimize and improve the generated results in a targeted manner. To address this issue, this paper conducts a multi-angle investigation and analysis of the performance of LLMs in Web site generation tasks. Firstly, Web generation requirements are collected, and effective prompt engineering is designed. These prompts are then input into different LLMs to initiate the self-iteration process. Next, the generated code is fed back into the LLM for security self-iteration, where the model performs vulnerability detection and repair on the code it has generated. The security-enhanced code is subsequently subjected to manual review, where it is evaluated using predefined quantitative metrics to generate indicator values. Finally, through testing, the quality, security, and code defects of the generated front-end and back-end Web code across different LLMs are analyzed, providing a comprehensive evaluation of the generation results. The experiments demonstrate that LLM systems perform well in completing and implementing the functions and layouts of pages in prompts for Web generation tasks, but there remains room for improvement in the security of the Web code.

Background Artificial intelligence (AI) offers significant opportunities to improve the field of implementation science by supporting key activities such as evidence synthesis, contextual analysis, and decision-making to promote the adoption and sustainability of evidence-based practices. This living scoping review aims to: (1) map applications of AI in implementation research and practice; (2) identify evaluation approaches, reported outcomes, and potential risks; and (3) synthesize reported research gaps and opportunities for advancing the use of AI in implementation science. Methods This scoping review will follow the Joanna Briggs Institute (JBI) methodology and the Cochrane guidance for living systematic reviews. A living scoping review is warranted to keep up with the rapid changes in AI and its growing use in implementation science. We will include empirical studies, systematic reviews, grey literature, and policy documents that describe or evaluate applications of AI to support implementation science across the steps of the Knowledge-to-Action (KTA) Model. AI methods and models of interest include machine learning, deep learning, natural language processing, large language models, and related technologies and approaches. A search strategy will be applied to bibliographic databases (MEDLINE, Embase, CINAHL, PsycINFO, IEEE Xplore, Web of Science), relevant journals, conference proceedings, and preprint servers. Two reviewers will independently screen studies and extract data on AI characteristics, specific implementation task according to the KTA Model, evaluation methods, outcome domains, risks, and research gaps. Extracted data will be analyzed descriptively and synthesized narratively using a mapping approach aligned with the KTA Model. Discussion This living review will consolidate the evidence base on how AI is applied across the spectrum of implementation science. It will inform researchers, policymakers, and practitioners seeking to harness AI to improve the adoption, scale-up, and sustainability of evidence-based interventions, while identifying areas for methodological advancement and risk mitigation. Review registration Open Science Framework, May 2025: https://doi.org/10.17605/OSF.IO/2Q5DV

Researchers in otolaryngology-head and neck surgery (OHNS) have sought to explore the potential of large language models (LLMs), but many publications do not include crucial information, such as prompting approach and model parameters. This has substantial implications for reproducibility, since LLMs can generate different output based on differences in "prompt engineering." We aimed to critically review methodological reporting and quality of LLM-focused literature in OHNS. Databases were searched in October 2024, including PubMed, Embase, Web of Science, ISCA Archive, IEEE Xplore, arXiv, medRxiv, and engRxiv. Abstract and full text review, as well as data extraction, were performed by two independent reviewers. All primary studies using LLMs within OHNS were included. From 925 abstracts retrieved, 117 were included. All studies used ChatGPT, with a minority (16.2%) including additional LLMs. Only 46.2% published direct quotations of all prompts. While the majority (76.9%) reported the number of prompts, only 6.8% rationalized this number, while 23.9% reported the number of runs per prompt. Most publications (73.5%) provided some description of prompt development, though only 11.1% explicitly described why specific decisions in prompt design were made, and only 6.0% reported prompt testing. There was no evidence that quality of methodology reporting was improving over time. LLM-focused literature in OHNS, while exploring many potentially fruitful avenues, demonstrates variable completeness in methodological reporting. This severely limits the generalizability of these studies and suggests that best practices could be further disseminated and enforced by researchers and journals.

Efficient processing of radiology reports for monitoring disease progression is crucial in oncology. Although large language models (LLMs) show promise in extracting structured information from medical reports, privacy concerns limit their clinical implementation. This study evaluates the feasibility and accuracy of two of the most recent Llama models for generating structured lymphoma progression reports from cross-sectional imaging data in a privacy-preserving, real-world clinical setting.This single-center, retrospective study included adult lymphoma patients who underwent cross-sectional imaging and treatment between July 2023 and July 2024. We established a chain-of-thought prompting strategy to leverage the locally deployed Llama-3.3-70B-Instruct and Llama-4-Scout-17B-16E-Instruct models to generate lymphoma disease progression reports across three iterations. Two radiologists independently scored nodal and extranodal involvement, as well as Lugano staging and treatment response classifications. For each LLM and task, we calculated the F1 score, accuracy, recall, precision, and specificity per label, as well as the case-weighted average with 95% confidence intervals (CIs).Both LLMs correctly implemented the template structure for all 65 patients included in this study. Llama-4-Scout-17B-16E-Instruct demonstrated significantly greater accuracy in extracting nodal and extranodal involvement information (nodal: 0.99 [95% CI = 0.98-0.99] vs. 0.97 [95% CI = 0.95-0.96], p < 0.001; extranodal: 0.99 [95% CI = 0.99-1.00] vs. 0.99 [95% CI = 0.98-0.99], p = 0.013). This difference was more pronounced when predicting Lugano stage and treatment response (stage: 0.85 [95% CI = 0.79-0.89] vs. 0.60 [95% CI = 0.53-0.67], p < 0.001; treatment response: 0.88 [95% CI = 0.83-0.92] vs. 0.65 [95% CI = 0.58-0.71], p < 0.001). Neither model produced hallucinations of newly involved nodal or extranodal sites. The highest relative error rates were found when interpreting the level of disease after treatment.In conclusion,privacy-preserving LLMs can effectively extract clinical information from lymphoma imaging reports. While they excel at data extraction, they are limited in their ability to generate new clinical inferences from the extracted information. Our findings suggest their potential utility in streamlining documentation and highlight areas requiring optimization before clinical implementation.

Food extrusion is a widely used processing technique that transforms raw ingredients into structured food products-foods with well-defined textures, shapes, and functionalities-through mechanical shear and thermal energy. Despite its broad industrial application, the absence of a standardised, structured dataset capturing extrusion research parameters has hindered research synthesis, product development, and process optimisation. To address this gap, we introduce a manually curated food extrusion literature dataset capturing publication details, product types, process parameters, formulation data, experimental variables, characterisation metrics, and study-level insights. However, while manually curated datasets are typically of high quality, their scope is limited by time and resource constraints. We propose a method to supplement the dataset using large language models (LLMs) and evaluate the accuracy of LLMs in extracting structured food extrusion data from the scientific literature. Our findings demonstrate that LLMs can effectively extract structured information. However, some challenges, such as hallucination and missing contextual details, remain, suggesting that human effort can be spent on validating the resulting data. This still represents significant time savings as validation is a less time-consuming task than data extraction. We argue that LLMs thus represent a viable tool in providing supplementary datasets, and we propose a method to leverage existing human efforts in dataset creation to improve data quality.

Data extraction from the published literature is the most laborious step in conducting living systematic reviews (LSRs). We aim to build a generalizable, automated data extraction workflow leveraging large language models (LLMs) that mimics the real-world 2-reviewer process. A dataset of 10 trials (22 publications) from a published LSR was used, focusing on 23 variables related to trial, population, and outcomes data. The dataset was split into prompt development (n = 5) and held-out test sets (n = 17). GPT-4-turbo and Claude-3-Opus were used for data extraction. Responses from the 2 LLMs were considered concordant if they were the same for a given variable. The discordant responses from each LLM were provided to the other LLM for cross-critique. Accuracy, ie, the total number of correct responses divided by the total number of responses, was computed to assess performance. In the prompt development set, 110 (96%) responses were concordant, achieving an accuracy of 0.99 against the gold standard. In the test set, 342 (87%) responses were concordant. The accuracy of the concordant responses was 0.94. The accuracy of the discordant responses was 0.41 for GPT-4-turbo and 0.50 for Claude-3-Opus. Of the 49 discordant responses, 25 (51%) became concordant after cross-critique, increasing accuracy to 0.76. Concordant responses by the LLMs are likely to be accurate. In instances of discordant responses, cross-critique can further increase the accuracy. Large language models, when simulated in a collaborative, 2-reviewer workflow, can extract data with reasonable performance, enabling truly "living" systematic reviews.

The integration of large language models (LLMs) into medical diagnostics has garnered substantial attention due to their potential to enhance diagnostic accuracy, streamline clinical workflows, and address health care disparities. However, the rapid evolution of LLM research necessitates a comprehensive synthesis of their applications, challenges, and future directions. This scoping review aimed to provide an overview of the current state of research regarding the use of LLMs in medical diagnostics. The study sought to answer four primary subquestions, as follows: (1) Which LLMs are commonly used? (2) How are LLMs assessed in diagnosis? (3) What is the current performance of LLMs in diagnosing diseases? (4) Which medical domains are investigating the application of LLMs? This scoping review was conducted according to the Joanna Briggs Institute Manual for Evidence Synthesis and adheres to the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews). Relevant literature was searched from the Web of Science, PubMed, Embase, IEEE Xplore, and ACM Digital Library databases from 2022 to 2025. Articles were screened and selected based on predefined inclusion and exclusion criteria. Bibliometric analysis was performed using VOSviewer to identify major research clusters and trends. Data extraction included details on LLM types, application domains, and performance metrics. The field is rapidly expanding, with a surge in publications after 2023. GPT-4 and its variants dominated research (70/95, 74% of studies), followed by GPT-3.5 (34/95, 36%). Key applications included disease classification (text or image-based), medical question answering, and diagnostic content generation. LLMs demonstrated high accuracy in specialties like radiology, psychiatry, and neurology but exhibited biases in race, gender, and cost predictions. Ethical concerns, including privacy risks and model hallucination, alongside regulatory fragmentation, were critical barriers to clinical adoption. LLMs hold transformative potential for medical diagnostics but require rigorous validation, bias mitigation, and multimodal integration to address real-world complexities. Future research should prioritize explainable artificial intelligence frameworks, specialty-specific optimization, and international regulatory harmonization to ensure equitable and safe clinical deployment.