搜索结果：GPT-55

GPT-4o is an autoregressive omni model that accepts as input any combination of text, audio, image, and video, and generates any combination of text, audio, and image outputs. It's trained end-to-end across text, vision, and audio, meaning all inputs and outputs are processed by the same neural network. GPT-4o can respond to audio inputs in as little as 232 milliseconds, with an average of 320 milliseconds, which is similar to human response time in conversation. It matches GPT-4 Turbo performance on text in English and code, with significant improvement on text in non-English languages, while also being much faster and 50\% cheaper in the API. GPT-4o is especially better at vision and audio understanding compared to existing models. In line with our commitment to building AI safely and consistent with our voluntary commitments to the White House, we are sharing the GPT-4o System Card, which includes our Preparedness Framework evaluations. In this System Card, we provide a detailed look at GPT-4o's capabilities, limitations, and safety evaluations across multiple categories, focusing on speech-to-speech while also evaluating text and image capabilities, and measures we've implemented to ensure the model is safe and aligned. We also include third-party assessments on dangerous capabilities, as well as discussion of potential societal impacts of GPT-4o's text and vision capabilities.

Abstract—Large Language Models (LLMs) suffer from inherent stochasticity, limiting their utility in high-stakes enterprise environments where determinism and auditability are required. This paper introduces the MFOUR Vibe Framework (MVF), a platform-agnostic architectural standard that transforms probabilistic natural language intent into deterministic software artifacts. We define a five-layer topology, comprising the Kernel Identity, Synaptic Routing, Interface Contracts, Context Anchoring, and the Mirror Test. Furthermore, we introduce The Vibe Integrity Score (VIS), a quantitative metric for evaluating the structural adherence of generative outputs. This specification provides the foundational schema and logic protocols for building "Glass Box" AI systems that are observable, secure, and commercially viable.

Instruction tuning large language models (LLMs) using machine-generated instruction-following data has improved zero-shot capabilities on new tasks, but the idea is less explored in the multimodal field. In this paper, we present the first attempt to use language-only GPT-4 to generate multimodal language-image instruction-following data. By instruction tuning on such generated data, we introduce LLaVA: Large Language and Vision Assistant, an end-to-end trained large multimodal model that connects a vision encoder and LLM for general-purpose visual and language understanding.Our early experiments show that LLaVA demonstrates impressive multimodel chat abilities, sometimes exhibiting the behaviors of multimodal GPT-4 on unseen images/instructions, and yields a 85.1% relative score compared with GPT-4 on a synthetic multimodal instruction-following dataset. When fine-tuned on Science QA, the synergy of LLaVA and GPT-4 achieves a new state-of-the-art accuracy of 92.53%. We make GPT-4 generated visual instruction tuning data, our model and code base publicly available.

Large language models (LLMs) have demonstrated remarkable capabilities in natural language understanding and generation across various domains, including medicine. We present a comprehensive evaluation of GPT-4, a state-of-the-art LLM, on medical competency examinations and benchmark datasets. GPT-4 is a general-purpose model that is not specialized for medical problems through training or engineered to solve clinical tasks. Our analysis covers two sets of official practice materials for the USMLE, a three-step examination program used to assess clinical competency and grant licensure in the United States. We also evaluate performance on the MultiMedQA suite of benchmark datasets. Beyond measuring model performance, experiments were conducted to investigate the influence of test questions containing both text and images on model performance, probe for memorization of content during training, and study probability calibration, which is of critical importance in high-stakes applications like medicine. Our results show that GPT-4, without any specialized prompt crafting, exceeds the passing score on USMLE by over 20 points and outperforms earlier general-purpose models (GPT-3.5) as well as models specifically fine-tuned on medical knowledge (Med-PaLM, a prompt-tuned version of Flan-PaLM 540B). In addition, GPT-4 is significantly better calibrated than GPT-3.5, demonstrating a much-improved ability to predict the likelihood that its answers are correct. We also explore the behavior of the model qualitatively through a case study that shows the ability of GPT-4 to explain medical reasoning, personalize explanations to students, and interactively craft new counterfactual scenarios around a medical case. Implications of the findings are discussed for potential uses of GPT-4 in medical education, assessment, and clinical practice, with appropriate attention to challenges of accuracy and safety.

The digitization of healthcare has facilitated the sharing and re-using of medical data but has also raised concerns about confidentiality and privacy. HIPAA (Health Insurance Portability and Accountability Act) mandates removing re-identifying information before the dissemination of medical records. Thus, effective and efficient solutions for de-identifying medical data, especially those in free-text forms, are highly needed. While various computer-assisted de-identification methods, including both rule-based and learning-based, have been developed and used in prior practice, such solutions still lack generalizability or need to be fine-tuned according to different scenarios, significantly imposing restrictions in wider use. The advancement of large language models (LLM), such as ChatGPT and GPT-4, have shown great potential in processing text data in the medical domain with zero-shot in-context learning, especially in the task of privacy protection, as these models can identify confidential information by their powerful named entity recognition (NER) capability. In this work, we developed a novel GPT4-enabled de-identification framework (``DeID-GPT") to automatically identify and remove the identifying information. Compared to existing commonly used medical text data de-identification methods, our developed DeID-GPT showed the highest accuracy and remarkable reliability in masking private information from the unstructured medical text while preserving the original structure and meaning of the text. This study is one of the earliest to utilize ChatGPT and GPT-4 for medical text data processing and de-identification, which provides insights for further research and solution development on the use of LLMs such as ChatGPT/GPT-4 in healthcare. Codes and benchmarking data information are available at https://github.com/yhydhx/ChatGPT-API.

Early work has found that large language models (LLMs) can generate persuasive content. However, evidence on whether they can also personalize arguments to individual attributes remains limited, despite being crucial for assessing misuse. This preregistered study examines AI-driven persuasion in a controlled setting, where participants engaged in short multiround debates. Participants were randomly assigned to 1 of 12 conditions in a 2 × 2 × 3 design: (1) human or GPT-4 debate opponent; (2) opponent with or without access to sociodemographic participant data; (3) debate topic of low, medium or high opinion strength. In debate pairs where AI and humans were not equally persuasive, GPT-4 with personalization was more persuasive 64.4% of the time (81.2% relative increase in odds of higher post-debate agreement; 95% confidence interval [+26.0%, +160.7%], P < 0.01; N = 900). Our findings highlight the power of LLM-based persuasion and have implications for the governance and design of online platforms.

BACKGROUND: Recent advancements in artificial intelligence, such as GPT-3.5 Turbo (OpenAI) and GPT-4, have demonstrated significant potential by achieving good scores on text-only United States Medical Licensing Examination (USMLE) exams and effectively answering questions from physicians. However, the ability of these models to interpret medical images remains underexplored. OBJECTIVE: This study aimed to comprehensively evaluate the performance, interpretability, and limitations of GPT-3.5 Turbo, GPT-4, and its successor, GPT-4 Vision (GPT-4V), specifically focusing on GPT-4V's newly introduced image-understanding feature. By assessing the models on medical licensing examination questions that require image interpretation, we sought to highlight the strengths and weaknesses of GPT-4V in handling complex multimodal clinical information, thereby exposing hidden flaws and providing insights into its readiness for integration into clinical settings. METHODS: This cross-sectional study tested GPT-4V, GPT-4, and ChatGPT-3.5 Turbo on a total of 227 multiple-choice questions with images from USMLE Step 1 (n=19), Step 2 clinical knowledge (n=14), Step 3 (n=18), the Diagnostic Radiology Qualifying Core Exam (DRQCE) (n=26), and AMBOSS question banks (n=150). AMBOSS provided expert-written hints and question difficulty levels. GPT-4V's accuracy was compared with 2 state-of-the-art large language models, GPT-3.5 Turbo and GPT-4. The quality of the explanations was evaluated by choosing human preference between an explanation by GPT-4V (without hint), an explanation by an expert, or a tie, using 3 qualitative metrics: comprehensive explanation, question information, and image interpretation. To better understand GPT-4V's explanation ability, we modified a patient case report to resemble a typical "curbside consultation" between physicians. RESULTS: For questions with images, GPT-4V achieved an accuracy of 84.2%, 85.7%, 88.9%, and 73.1% in Step 1, Step 2 clinical knowledge, Step 3 of USMLE, and DRQCE, respectively. It outperformed GPT-3.5 Turbo (42.1%, 50%, 50%, 19.2%) and GPT-4 (63.2%, 64.3%, 66.7%, 26.9%). When GPT-4V answered correctly, its explanations were nearly as good as those provided by domain experts from AMBOSS. However, incorrect answers often had poor explanation quality: 18.2% (10/55) contained inaccurate text, 45.5% (25/55) had inference errors, and 76.3% (42/55) demonstrated image misunderstandings. With human expert assistance, GPT-4V reduced errors by an average of 40% (22/55). GPT-4V accuracy improved with hints, maintaining stable performance across difficulty levels, while medical student performance declined as difficulty increased. In a simulated curbside consultation scenario, GPT-4V required multiple specific prompts to interpret complex case data accurately. CONCLUSIONS: GPT-4V achieved high accuracy on multiple-choice questions with images, highlighting its potential in medical assessments. However, significant shortcomings were observed in the quality of explanations when questions were answered incorrectly, particularly in the interpretation of images, which could not be efficiently resolved through expert interaction. These findings reveal hidden flaws in the image interpretation capabilities of GPT-4V, underscoring the need for more comprehensive evaluations beyond multiple-choice questions before integrating GPT-4V into clinical settings.

BACKGROUND: The integration of artificial intelligence (AI) in healthcare has rapidly expanded, particularly in clinical decision-making. Large language models (LLMs) such as GPT-4 and GPT-3.5 have shown potential in various medical applications, including diagnostics and treatment planning. However, their efficacy in specialized fields like sports surgery and physiotherapy remains underexplored. This study aims to compare the performance of GPT-4 and GPT-3.5 in clinical decision-making within these domains using a structured assessment approach. METHODS: This cross-sectional study included 56 professionals specializing in sports surgery and physiotherapy. Participants evaluated 10 standardized clinical scenarios generated by GPT-4 and GPT-3.5 using a 5-point Likert scale. The scenarios encompassed common musculoskeletal conditions, and assessments focused on diagnostic accuracy, treatment appropriateness, surgical technique detailing, and rehabilitation plan suitability. Data were collected anonymously via Google Forms. Statistical analysis included paired t-tests for direct model comparisons, one-way ANOVA to assess performance across multiple criteria, and Cronbach's alpha to evaluate inter-rater reliability. RESULTS: GPT-4 significantly outperformed GPT-3.5 across all evaluated criteria. Paired t-test results (t(55) = 10.45, p < 0.001) demonstrated that GPT-4 provided more accurate diagnoses, superior treatment plans, and more detailed surgical recommendations. ANOVA results confirmed the higher suitability of GPT-4 in treatment planning (F(1, 55) = 35.22, p < 0.001) and rehabilitation protocols (F(1, 55) = 32.10, p < 0.001). Cronbach's alpha values indicated higher internal consistency for GPT-4 (α = 0.478) compared to GPT-3.5 (α = 0.234), reflecting more reliable performance. CONCLUSIONS: GPT-4 demonstrates superior performance compared to GPT-3.5 in clinical decision-making for sports surgery and physiotherapy. These findings suggest that advanced AI models can aid in diagnostic accuracy, treatment planning, and rehabilitation strategies. However, AI should function as a decision-support tool rather than a substitute for expert clinical judgment. Future studies should explore the integration of AI into real-world clinical workflows, validate findings using larger datasets, and compare additional AI models beyond the GPT series.

The Generative Pre-trained Transformer (GPT) represents a notable breakthrough in the domain of natural language processing, which is propelling us toward the development of machines that can understand and communicate using language in a manner that closely resembles that of humans. GPT is based on the transformer architecture, a deep neural network designed for natural language processing tasks. Due to their impressive performance on natural language processing tasks and ability to effectively converse, GPT have gained significant popularity among researchers and industrial communities, making them one of the most widely used and effective models in natural language processing and related fields, which motivated to conduct this review. This review provides a detailed overview of the GPT, including its architecture, working process, training procedures, enabling technologies, and its impact on various applications. In this review, we also explored the potential challenges and limitations of a GPT. Furthermore, we discuss potential solutions and future directions. Overall, this paper aims to provide a comprehensive understanding of GPT, its enabling technologies, their impact on various applications, emerging challenges, and potential solutions.

Background Large language models (LLMs) have raised both interest and concern in the academic community. They offer the potential for automating literature search and synthesis for systematic reviews but raise concerns regarding their reliability, as the tendency to generate unsupported (hallucinated) content persist. Objective The aim of the study is to assess the performance of LLMs such as ChatGPT and Bard (subsequently rebranded Gemini) to produce references in the context of scientific writing. Methods The performance of ChatGPT and Bard in replicating the results of human-conducted systematic reviews was assessed. Using systematic reviews pertaining to shoulder rotator cuff pathology, these LLMs were tested by providing the same inclusion criteria and comparing the results with original systematic review references, serving as gold standards. The study used 3 key performance metrics: recall, precision, and F1-score, alongside the hallucination rate. Papers were considered “hallucinated” if any 2 of the following information were wrong: title, first author, or year of publication. Results In total, 11 systematic reviews across 4 fields yielded 33 prompts to LLMs (3 LLMs×11 reviews), with 471 references analyzed. Precision rates for GPT-3.5, GPT-4, and Bard were 9.4% (13/139), 13.4% (16/119), and 0% (0/104) respectively (P&lt;.001). Recall rates were 11.9% (13/109) for GPT-3.5 and 13.7% (15/109) for GPT-4, with Bard failing to retrieve any relevant papers (P&lt;.001). Hallucination rates stood at 39.6% (55/139) for GPT-3.5, 28.6% (34/119) for GPT-4, and 91.4% (95/104) for Bard (P&lt;.001). Further analysis of nonhallucinated papers retrieved by GPT models revealed significant differences in identifying various criteria, such as randomized studies, participant criteria, and intervention criteria. The study also noted the geographical and open-access biases in the papers retrieved by the LLMs. Conclusions Given their current performance, it is not recommended for LLMs to be deployed as the primary or exclusive tool for conducting systematic reviews. Any references generated by such models warrant thorough validation by researchers. The high occurrence of hallucinations in LLMs highlights the necessity for refining their training and functionality before confidently using them for rigorous academic purposes.

The social and behavioral sciences have been increasingly using automated text analysis to measure psychological constructs in text. We explore whether GPT, the large-language model (LLM) underlying the AI chatbot ChatGPT, can be used as a tool for automated psychological text analysis in several languages. Across 15 datasets ( n = 47,925 manually annotated tweets and news headlines), we tested whether different versions of GPT (3.5 Turbo, 4, and 4 Turbo) can accurately detect psychological constructs (sentiment, discrete emotions, offensiveness, and moral foundations) across 12 languages. We found that GPT ( r = 0.59 to 0.77) performed much better than English-language dictionary analysis ( r = 0.20 to 0.30) at detecting psychological constructs as judged by manual annotators. GPT performed nearly as well as, and sometimes better than, several top-performing fine-tuned machine learning models. Moreover, GPT’s performance improved across successive versions of the model, particularly for lesser-spoken languages, and became less expensive. Overall, GPT may be superior to many existing methods of automated text analysis, since it achieves relatively high accuracy across many languages, requires no training data, and is easy to use with simple prompts (e.g., “is this text negative?”) and little coding experience. We provide sample code and a video tutorial for analyzing text with the GPT application programming interface. We argue that GPT and other LLMs help democratize automated text analysis by making advanced natural language processing capabilities more accessible, and may help facilitate more cross-linguistic research with understudied languages.

Here we demonstrate that the large language model GPT-4 can accurately annotate cell types using marker gene information in single-cell RNA sequencing analysis. When evaluated across hundreds of tissue and cell types, GPT-4 generates cell type annotations exhibiting strong concordance with manual annotations. This capability can considerably reduce the effort and expertise required for cell type annotation. Additionally, we have developed an R software package GPTCelltype for GPT-4's automated cell type annotation.

There is a constant need for educators to develop and maintain effective up-to-date assessments. While there is a growing body of research in computing education on utilizing large language models (LLMs) in generation and engagement with coding exercises, the use of LLMs for generating programming MCQs has not been extensively explored. We analyzed the capability of GPT-4 to produce multiple-choice questions (MCQs) aligned with specific learning objectives (LOs) from Python programming classes in higher education. Specifically, we developed an LLM-powered (GPT-4) system for generation of MCQs from high-level course context and module-level LOs. We evaluated 651 LLM-generated and 449 human-crafted MCQs aligned to 246 LOs from 6 Python courses. We found that GPT-4 was capable of producing MCQs with clear language, a single correct choice, and high-quality distractors. We also observed that the generated MCQs appeared to be well-aligned with the LOs. Our findings can be leveraged by educators wishing to take advantage of the state-of-the-art generative models to support MCQ authoring efforts.

GPT (Generative Pre-trained Transformer) represents advanced language models that have significantly reshaped the academic writing landscape. These sophisticated language models offer invaluable support throughout all phases of research work, facilitating idea generation, enhancing drafting processes, and overcoming challenges like writer’s block. Their capabilities extend beyond conventional applications, contributing to critical analysis, data augmentation, and research design, thereby elevating the efficiency and quality of scholarly endeavors. Strategically narrowing its focus, this review explores alternative dimensions of GPT and LLM applications, specifically data augmentation and the generation of synthetic data for research. Employing a meticulous examination of 412 scholarly works, it distills a selection of 77 contributions addressing three critical research questions: (1) GPT on Generating Research data, (2) GPT on Data Analysis, and (3) GPT on Research Design. The systematic literature review adeptly highlights the central focus on data augmentation, encapsulating 48 pertinent scholarly contributions, and extends to the proactive role of GPT in critical analysis of research data and shaping research design. Pioneering a comprehensive classification framework for “GPT’s use on Research Data”, the study classifies existing literature into six categories and 14 sub-categories, providing profound insights into the multifaceted applications of GPT in research data. This study meticulously compares 54 pieces of literature, evaluating research domains, methodologies, and advantages and disadvantages, providing scholars with profound insights crucial for the seamless integration of GPT across diverse phases of their scholarly pursuits.

Based on breast imaging reports written in three languages, GPT-3.5, GPT-4, and Google Bard achieved moderate agreement with human reader–assigned Breast Imaging Reporting and Data System categories but also yielded a high percentage of discordant category assignments that would negatively impact clinical management.

BACKGROUND: Chat Generative Pre-trained Transformer (ChatGPT) is a 175-billion-parameter natural language processing model that can generate conversation-style responses to user input. OBJECTIVE: This study aimed to evaluate the performance of ChatGPT on questions within the scope of the United States Medical Licensing Examination (USMLE) Step 1 and Step 2 exams, as well as to analyze responses for user interpretability. METHODS: We used 2 sets of multiple-choice questions to evaluate ChatGPT's performance, each with questions pertaining to Step 1 and Step 2. The first set was derived from AMBOSS, a commonly used question bank for medical students, which also provides statistics on question difficulty and the performance on an exam relative to the user base. The second set was the National Board of Medical Examiners (NBME) free 120 questions. ChatGPT's performance was compared to 2 other large language models, GPT-3 and InstructGPT. The text output of each ChatGPT response was evaluated across 3 qualitative metrics: logical justification of the answer selected, presence of information internal to the question, and presence of information external to the question. RESULTS: Of the 4 data sets, AMBOSS-Step1, AMBOSS-Step2, NBME-Free-Step1, and NBME-Free-Step2, ChatGPT achieved accuracies of 44% (44/100), 42% (42/100), 64.4% (56/87), and 57.8% (59/102), respectively. ChatGPT outperformed InstructGPT by 8.15% on average across all data sets, and GPT-3 performed similarly to random chance. The model demonstrated a significant decrease in performance as question difficulty increased (P=.01) within the AMBOSS-Step1 data set. We found that logical justification for ChatGPT's answer selection was present in 100% of outputs of the NBME data sets. Internal information to the question was present in 96.8% (183/189) of all questions. The presence of information external to the question was 44.5% and 27% lower for incorrect answers relative to correct answers on the NBME-Free-Step1 (P<.001) and NBME-Free-Step2 (P=.001) data sets, respectively. CONCLUSIONS: ChatGPT marks a significant improvement in natural language processing models on the tasks of medical question answering. By performing at a greater than 60% threshold on the NBME-Free-Step-1 data set, we show that the model achieves the equivalent of a passing score for a third-year medical student. Additionally, we highlight ChatGPT's capacity to provide logic and informational context across the majority of answers. These facts taken together make a compelling case for the potential applications of ChatGPT as an interactive medical education tool to support learning.

Abstract Large language models (LLMs) have shown superior performance in various areas. And LLMs have the potential to revolutionize data management by serving as the "brain" of next-generation database systems. However, there are several challenges that utilize LLMs to optimize databases. First, it is challenging to provide appropriate prompts (e.g., instructions and demonstration examples) to enable LLMs to understand the database optimization problems. Second, LLMs only capture the logical database characters (e.g., SQL semantics) but are not aware of physical characters (e.g., data distributions), and it requires to fine-tune LLMs to capture both physical and logical information. Third, LLMs are not well trained for databases with strict constraints (e.g., query plan equivalence) and privacy-preserving requirements, and it is challenging to train database-specific LLMs while ensuring database privacy. To overcome these challenges, this vision paper proposes a LLM-based database framework (), including automatic prompt generation, DB-specific model fine-tuning, and DB-specific model design and pre-training. Preliminary experiments show that achieves relatively good performance in database tasks like query rewrite and index tuning. The source code and datasets are available at github.com/TsinghuaDatabaseGroup/DB-GPT.

The integration of artificial intelligence into scientific research opens new avenues with the advent of GPT-4V, a large language model equipped with vision capabilities.

As Generative AI rises in adoption, its use has expanded to include domains such as hiring and recruiting. However, without examining the potential of bias, this may negatively impact marginalized populations, including people with disabilities. To address this important concern, we present a resume audit study, in which we ask ChatGPT (specifically, GPT-4) to rank a resume against the same resume enhanced with an additional leadership award, scholarship, panel presentation, and membership that are disability-related. We find that GPT-4 exhibits prejudice towards these enhanced CVs. Further, we show that this prejudice can be quantifiably reduced by training a custom GPTs on principles of DEI and disability justice. Our study also includes a unique qualitative analysis of the types of direct and indirect ableism GPT-4 uses to justify its biased decisions and suggest directions for additional bias mitigation work. Additionally, since these justifications are presumably drawn from training data containing real-world biased statements made by humans, our analysis suggests additional avenues for understanding and addressing human bias.