When geoscience meets generative AI and large language models: Foundations, trends, and future challenges

Evaluating gpt-4 for zero-shot classification of bleeding and clotting events: Can large language models serve as second reviewers?

Problem definition: Large language models (LLMs) are being increasingly leveraged in business and consumer decision-making processes. Because LLMs learn from human data and feedback, which can be biased, determining whether LLMs exhibit human-like behavioral decision biases (e.g., base-rate neglect, risk aversion, confirmation bias, etc.) is crucial prior to implementing LLMs into decision-making contexts and workflows. To understand this, we examine 18 common human biases that are important in operations management (OM) using the dominant LLM, ChatGPT. Methodology/results: We perform experiments where GPT-3.5 and GPT-4 act as participants to test these biases using vignettes adapted from the literature (“standard context”) and variants reframed in inventory and general OM contexts. In almost half of the experiments, Generative Pre-trained Transformer (GPT) mirrors human biases, diverging from prototypical human responses in the remaining experiments. We also observe that GPT models have a notable level of consistency between the standard and OM-specific experiments as well as across temporal versions of the GPT-3.5 model. Our comparative analysis between GPT-3.5 and GPT-4 reveals a dual-edged progression of GPT’s decision making, wherein GPT-4 advances in decision-making accuracy for problems with well-defined mathematical solutions while simultaneously displaying increased behavioral biases for preference-based problems. Managerial implications: First, our results highlight that managers will obtain the greatest benefits from deploying GPT to workflows leveraging established formulas. Second, that GPT displayed a high level of response consistency across the standard, inventory, and non-inventory operational contexts provides optimism that LLMs can offer reliable support even when details of the decision and problem contexts change. Third, although selecting between models, like GPT-3.5 and GPT-4, represents a trade-off in cost and performance, our results suggest that managers should invest in higher-performing models, particularly for solving problems with objective solutions. Funding: This work was supported by the Social Sciences and Humanities Research Council of Canada [Grant SSHRC 430-2019-00505]. The authors also gratefully acknowledge the Smith School of Business at Queen’s University for providing funding to support Y. Chen’s postdoctoral appointment. Supplemental Material: The online appendix is available at https://doi.org/10.1287/msom.2023.0279 .

The introduction of large language models (LLMs), such as Generative Pre-trained Transformer 4 (GPT-4; OpenAI), has generated significant interest in health care, yet studies evaluating their performance in a clinical setting are lacking. Determination of clinical acuity, a measure of a patient's illness severity and level of required medical attention, is one of the foundational elements of medical reasoning in emergency medicine. To determine whether an LLM can accurately assess clinical acuity in the emergency department (ED). This cross-sectional study identified all adult ED visits from January 1, 2012, to January 17, 2023, at the University of California, San Francisco, with a documented Emergency Severity Index (ESI) acuity level (immediate, emergent, urgent, less urgent, or nonurgent) and with a corresponding ED physician note. A sample of 10 000 pairs of ED visits with nonequivalent ESI scores, balanced for each of the 10 possible pairs of 5 ESI scores, was selected at random. The potential of the LLM to classify acuity levels of patients in the ED based on the ESI across 10 000 patient pairs. Using deidentified clinical text, the LLM was queried to identify the patient with a higher-acuity presentation within each pair based on the patients' clinical history. An earlier LLM was queried to allow comparison with this model. Accuracy score was calculated to evaluate the performance of both LLMs across the 10 000-pair sample. A 500-pair subsample was manually classified by a physician reviewer to compare performance between the LLMs and human classification. From a total of 251 401 adult ED visits, a balanced sample of 10 000 patient pairs was created wherein each pair comprised patients with disparate ESI acuity scores. Across this sample, the LLM correctly inferred the patient with higher acuity for 8940 of 10 000 pairs (accuracy, 0.89 [95% CI, 0.89-0.90]). Performance of the comparator LLM (accuracy, 0.84 [95% CI, 0.83-0.84]) was below that of its successor. Among the 500-pair subsample that was also manually classified, LLM performance (accuracy, 0.88 [95% CI, 0.86-0.91]) was comparable with that of the physician reviewer (accuracy, 0.86 [95% CI, 0.83-0.89]). In this cross-sectional study of 10 000 pairs of ED visits, the LLM accurately identified the patient with higher acuity when given pairs of presenting histories extracted from patients' first ED documentation. These findings suggest that the integration of an LLM into ED workflows could enhance triage processes while maintaining triage quality and warrants further investigation.

e13630 Background: As many as 60% of prior authorization requests are denied, yet coverage approval occurs for more than 60% of appeals for some therapies. Appeal processes encumber providers and increase burnout, but large language models (LLMs) may aid providers by drafting appeal letters. We evaluated LLM performance at this task for radiotherapy denials. Methods: Three commercially accessible LLMs were evaluated: generative pre-trained transformer 3.5 (GPT3.5), GPT4, and GPT4+web with internet search capacity (OpenAI, Inc., San Francisco, CA). A fourth LLM, GPT3.5-FT, was developed by fine-tuning GPT3.5 in a HIPAA-complaint local environment. The fine-tuning training data comprised 53 insurance denial appeal letters prepared by radiation oncologists and paired prompts describing the clinical history and appeal intent. Training data were enriched in appeal letters for proton radiotherapy, stereotactic body radiotherapy, and image-guided radiotherapy for myriad clinical scenarios. Twenty prompts, each requesting a letter for a simulated patient history, were programmatically presented to the LLMs. Three radiation oncologists, who were blinded to the LLM source, scored letter outputs across four domains: language syntax and semantics, clinical detail inclusion, clinical reasoning validity, and overall readiness for insurer submission. Additionally, one radiation oncologist scored the authenticity and relevance of literature sources cited in output letters, which were requested by several test prompts. Interobserver agreement between radiation oncologist scores was determined by Cohen’s kappa coefficient. Scores were compared between LLMs with non-parametric statistical tests. Results: Agreement between radiation oncologists’ scores was moderate-to-excellent across all domains (median κ = 0.68, minimum κ = 0.41). GPT3.5, GPT4, and GPT4+web drafted letters that, by mode average, were semantically and syntactically clear, included all provided clinical history without confabulation, clinically reasoned with few necessary revisions, and overall were submissible to an insurer with minor revisions. GPT4 and GPT4+web clinically reasoned better than GPT3.5 (p values < 0.001). In contrast, GPT3.5-FT performance was inferior to other LLMs across all domains (p values < 0.001). LLMs were poor at identifying, citing, and summarizing relevant literature unless provided in the prompt. Conclusions: LLMs can draft insurance appeal letters for radiotherapy services that require few revisions yet are poor at referencing relevant literature. Contrary to our hypothesis, fine-tuning with data from our department compromised LLM performance.

PurposeLarge language models (LLMs) like Generative Pre-trained Transformer 4 (GPT-4) can assist in detecting errors in radiology reports, but privacy concerns limit their clinical applicability. This study compares closed-source and privacy-compliant open-source LLMs for detecting common errors in radiology reports.Materials and methodsA total of 120 radiology reports were compiled (30 each from X-ray, ultrasound, CT, and MRI). Subsequently, 397 errors from five categories (typographical, numerical, findings-impression discrepancies, omission/insertion, interpretation) were inserted into 100 of these reports; 20 reports were left unchanged. Two open-source models (Llama 3-70b, Mixtral 8x22b) and two commercial closed-source (GPT-4, GPT-4o) were tasked with error detection using identical prompts. The Kruskall–Wallis test and paired t-test were used for statistical analysis.ResultsOpen-source LLMs required less processing time per radiology report than closed-source LLMs (6 ± 2 s vs. 13 ± 4 s; p < 0.001). Closed-source LLMs achieved higher error detection rates than open-source LLMs (GPT-4o: 88% [348/397; 95% CI: 86, 92], GPT-4: 83% [328/397; 95% CI: 80, 87], Llama 3-70b: 79% [311/397; 95% CI: 76, 83], Mixtral 8x22b: 73% [288/397; 95% CI: 68, 77]; p < 0.001). Numerical errors (88% [67/76; 95% CI: 82, 93]) were detected significantly more often than typographical errors (75% [65/86; 95% CI: 68, 82]; p = 0.02), discrepancies between findings and impression (73% [73/101; 95% CI: 67, 80]; p < 0.01), and interpretation errors (70% [50/71; 95% CI: 62, 78]; p = 0.001).ConclusionOpen-source LLMs demonstrated effective error detection, albeit with comparatively lower accuracy than commercial closed-source models, and have potential for clinical applications when deployed via privacy-compliant local hosting solutions.Key PointsQuestionCan privacy-compliant open-source large language models (LLMs) match the error-detection performance of commercial non-privacy-compliant closed-source models in radiology reports?FindingsClosed-source LLMs achieved slightly higher accuracy in detecting radiology report errors than open-source models, with Llama 3-70b yielding the best results among the open-source models.Clinical relevanceOpen-source LLMs offer a privacy-compliant alternative for automated error detection in radiology reports, improving clinical workflow efficiency while ensuring patient data confidentiality. Further refinement could enhance their accuracy, contributing to better diagnosis and patient care.Graphical

Brief hospital course (BHC) summaries are clinical documents that summarize a patient's hospital stay. While large language models (LLMs) depict remarkable capabilities in automating real-world tasks, their capabilities for healthcare applications such as synthesizing BHCs from clinical notes have not been shown. We introduce a novel preprocessed dataset, the MIMIC-IV-BHC, encapsulating clinical note and BHC pairs to adapt LLMs for BHC synthesis. Furthermore, we introduce a benchmark of the summarization performance of 2 general-purpose LLMs and 3 healthcare-adapted LLMs. Using clinical notes as input, we apply prompting-based (using in-context learning) and fine-tuning-based adaptation strategies to 3 open-source LLMs (Clinical-T5-Large, Llama2-13B, and FLAN-UL2) and 2 proprietary LLMs (Generative Pre-trained Transformer [GPT]-3.5 and GPT-4). We evaluate these LLMs across multiple context-length inputs using natural language similarity metrics. We further conduct a clinical study with 5 clinicians, comparing clinician-written and LLM-generated BHCs across 30 samples, focusing on their potential to enhance clinical decision-making through improved summary quality. We compare reader preferences for the original and LLM-generated summary using Wilcoxon signed-rank tests. We further request optional qualitative feedback from clinicians to gain deeper insights into their preferences, and we present the frequency of common themes arising from these comments. The Llama2-13B fine-tuned LLM outperforms other domain-adapted models given quantitative evaluation metrics of Bilingual Evaluation Understudy (BLEU) and Bidirectional Encoder Representations from Transformers (BERT)-Score. GPT-4 with in-context learning shows more robustness to increasing context lengths of clinical note inputs than fine-tuned Llama2-13B. Despite comparable quantitative metrics, the reader study depicts a significant preference for summaries generated by GPT-4 with in-context learning compared to both Llama2-13B fine-tuned summaries and the original summaries (P<.001), highlighting the need for qualitative clinical evaluation. We release a foundational clinically relevant dataset, the MIMIC-IV-BHC, and present an open-source benchmark of LLM performance in BHC synthesis from clinical notes. We observe high-quality summarization performance for both in-context proprietary and fine-tuned open-source LLMs using both quantitative metrics and a qualitative clinical reader study. Our research effectively integrates elements from the data assimilation pipeline: our methods use (1) clinical data sources to integrate, (2) data translation, and (3) knowledge creation, while our evaluation strategy paves the way for (4) deployment.

This paper presents a comprehensive survey of the applications, challenges, and limitations of Generative AI (GenAI) in enhancing threat intelligence within cybersecurity, supported by real-world case studies. We examine a wide range of data sources in Cyber Threat Intelligence (CTI), including security reports, blogs, social media, network traffic, malware samples, dark web data, and threat intelligence platforms (TIPs). This survey provides a full reference for integrating GenAI into CTI. We discuss various GenAI models such as Large Language Models (LLMs) and Deep Generative Models (DGMs) like Variational Autoencoders (VAEs), Generative Adversarial Networks (GANs), and Diffusion Models, explaining their roles in detecting and addressing complex cyber threats. The survey highlights key applications in areas such as malware detection, network traffic analysis, phishing detection, threat actor attribution, and social engineering defense. We also explore critical challenges in deploying GenAI, including data privacy, security concerns, and the need for interpretable and transparent models. As regulations like the European Commission’s AI Act emerge, ensuring trustworthy AI solutions is becoming more crucial. Real-world case studies, such as the impact of the WannaCry ransomware, the rise of deepfakes, and AI-driven social engineering, demonstrate both the potential and current limitations of GenAI in CTI. Our goal is to provide foundational insights and strategic direction for advancing GenAI’s role in future cybersecurity frameworks, emphasizing the importance of innovation, adaptability, and ongoing learning to enhance resilience against evolving cyber threats. Ultimately, this survey offers critical insights into how GenAI can shape the future of cybersecurity by addressing key challenges and providing actionable guidance for effective implementation.

Generative AI in cybersecurity: A comprehensive review of LLM applications and vulnerabilities

IntroductionThe risk and opportunity of Large Language Models (LLMs) in medical education both rest in their imitation of human communication. Future doctors working with generative artificial intelligence (AI) need to judge the value of any outputs from LLMs to safely direct the management of patients. We set out to investigate medical students’ ability to evaluate LLM responses to clinical vignettes, identify which prior learning they utilised to scrutinise the LLM answers, and assess their awareness of ‘clinical prompt engineering’.MethodsFinal year medical students were asked in a survey to assess the accuracy of the answers provided by generative pre-trained transformer (GPT) 3.5 in response to ten clinical scenarios, five of which GPT 3.5 had answered incorrectly, and to identify which prior training enabled them to evaluate the GPT 3.5 output. A content analysis was conducted amongst 148 consenting medical students.ResultsThe median percentage of students who correctly evaluated the LLM output was 56%. Students reported interactive case-based and pathology teaching using questions to be the most helpful training provided by the medical school for evaluating AI outputs. Only 5% were familiar with the concept of ‘clinical prompt engineering’.ConclusionPathology and interactive case-based teaching using questions were the self-reported best training for medical students to safely interact with the outputs of LLMs. This study can inform the design of medical training for future doctors graduating into AI-enhanced health services.

Recent years have witnessed notable progress in Language Model (LM) technology, especially with the introduction of Large Language Models (LLMs). With the use of complex neural networks and enormous volumes of data, these models—like the GPT (Generative Pre-trained Transformer) series—have completely changed the field of natural language processing. This study offers a thorough analysis of LLMs, examining their uses as well as the difficulties and moral issues that come with implementing LLMs in practical settings. Moreover, it investigates the wide range of uses of LLMs in many fields, such as question answering, drug discovery, language translation, and text production. By means of this review, we hope to offer ideas on future directions in this quickly developing field as well as insights into the state-of-the-art in LLM research today. Key Words: Large Language Models, LangChain, Natural language processing, GPT, ChatGPT, AI chatbots, Indirect Prompt Injection

​Purpose The purpose of this study was to evaluate the capabilities of large language models (LLMs) in understanding radiation safety and protection. We assessed the performance of generative pe-trained transformer (GPT)-4(OpenAI, USA) and Gemini Advanced (Google DeepMind, London) using questions from the First-Class Radiation Protection Supervisor Examination in Japan. Methods The study involved GPT-4 and Gemini Advanced answering questions from the 68th First-Class Radiation Protection Supervisor Examination in Japan. The number of correct and incorrect answers based on the subject, the presence or absence of calculation, the passage length, and the format (textual or graphical questions) were analyzed in this study. Comparisons of the results between GPT-4 and Gemini Advanced were performed. Results The overall accuracy rates of GPT-4 and Gemini Advanced were 71.0% and 65.3%, respectively. A significant difference was observed in the subject (P < 0.0001 in GPT-4 and P = 0.0127 in Gemini Advanced). The accuracy rate of laws and regulations was lower than in the other subjects. There was no significant difference in the presence or absence of calculation or the passage length. The performance of both LLMs was significantly better in textual questions than in graphical questions (P = 0.0003 in GPT-4 and P < 0.0001 in Gemini Advanced). The performance of the two LLMs did not differ significantly based on the subject, the presence or absence of calculation, the passage length, or the format. Conclusions GPT-4 and Gemini Advanced demonstrated sufficient understanding of physics, chemistry, biology, and practical operations to meet the passing standard for the average score. However, in laws and regulations, their performance was insufficient, possibly due to frequent revisions and the complexity of detailed regulations, and further machine learning is required.

Large language models (LLMs), and generative AI generally, raise significant concerns regarding human rights. Their promise in finding insights in patterns of data have to be weighed against potential risks to individuals and societies. The typical perspective, which emphasizes accuracy, capability, or scope of such systems, overlooks the fact that generative AI technologies exploit massive collections of data about human behaviors, thoughts, and ideas. The datafication of human life should be examined through the lens of human rights, specifically with regard to autonomy, dignity, equality, and community. This piece argues that discussions about LLMs and generative AI are inherently linked to data originated from individuals, whose information are embedded in the training data. Data are human rights issues because information about individuals are buried in the data. Technical solutions alone are insufficient to address the human rights distortions produced by LLMs. Policy should focus instead on the fact that data are collected on rights-bearing individuals and groups who have been given very little leeway to discuss the implications of or choose to be in the enterprise of creating generative AI.

Recent breakthroughs in artificial intelligence (AI) research include advancements in natural language processing (NLP) achieved by large language models (LLMs), and; in particular, generative pre–trained transformer (GPT) architectures. The latest GPT developed by OpenAI, GPT–4, has shown remarkable intelligence across various domains and tasks. It exhibits capabilities in abstraction, comprehension, vision, computer coding, mathematics, and more, suggesting it to be a significant step towards artificial general intelligence (AGI), a level of AI that possesses capabilities similar to human intelligence. This paper explores this AGI, its knowledge diffusive and societal influences, and its governance. In addition to coverage of the major associated topics studied in the literature, and making up for their loopholes, we scrutinize how GPT-4 can facilitate the diffusion of knowledge across different areas of science by promoting their interpretability and explainability (IE) to inexperts. Where applicable, the topics are also accompanied by their specific potential implications on medical imaging.

Pilot evaluation of a large language model-mediated pre-consultation interview for vestibular disorders.

The emergence of generative AI (GenAI) is a major driving force behind the modern data science ecosystem, a field that exploits data as the central asset for actionable insights. Analogously, GenAI is a form of artificial intelligence which learns from massive datasets to generate new data, showcasing human-like creativity in text, images to code, speech, and video. Two critical pillars of the GenAI technology are large language models (LLMs) and vector data. In particular, LLMs are a category of genAI models that emphasize on generating new text contents. On the other hand, there is also an upsurge of dense, high-dimensional, billion-scale vector data from deep learning models that embed complex data, e.g., text, multimedia, graphs, and tables into vector representations aiming to preserve semantic similarity. Since LLMs operate on vector data at various stages consisting of pre-training, fine-tuning, inference, and retrieval-augmented generation (RAG), coupling large language models with vector data management is essential for enhancing data science services with cross-modal data querying and generation. It creates new opportunities and challenges in areas such as accuracy, consistency, efficiency, scalability, privacy, fairness, explainability, data regulations, software-hardware collaboration, and cloud-native systems. The workshop aims to advance the understanding of how LLMs and vector data management can cooperatively contribute to data science solutions.