Domain-specific Expertise Research Articles

The role of registerial expertise in texture re-creation in medical translation

Abstract This article investigates how an important aspect of translators’ registerial expertise — domain-specific (medical) training and experience — may have consequences for the texture of a specialised translation, i.e. the translations of the Chinese medicine classic Huang Di Nei Jing. Through a fine-grained analysis of cohesion and coherence, this study demonstrates that a translator with a higher level of domain-specific expertise tends to produce a translation (i) that is more lexically explicit and cohesively harmonious, (ii) with a richer semantic variety, more extended cohesive chains and cross-chain interactions and (iii) having a higher degree of definitiveness. The findings suggest that a translator’s domain-specific expertise could have measurable consequences for the texture of the target text.

Random image masking and in-batch feature mixing for self-supervised learning

Contrastive learning has already had a significant impact in the field of self-supervised learning. The contrast of positive and negative samples is critical for contrastive learning. Recently, a revolutionary breakthrough has revealed that it is possible to learn meaningful representations without the need of negative samples. Nevertheless, using two randomly augmented views of the same instance as positive samples inevitably leads to its limitations. The design of positive samples becomes critically important and often necessitates domain-specific expertise. These methods invariably emphasize maximizing the similarity between two views, with a focus on global information invariance: different views of the same image yield approximately similar representations after encoding. Hence, we propose a novel methodology aimed at generating more intricate positive instances at both the image and feature level, termed random image masking and in-batch feature mixing. The former introduces local information loss through random masking of images, compelling the model to learn generalizable representations that focus on local information. The latter generates virtual positive samples by mixing samples within the batch in feature space, breaking free from the limitations of traditional data augmentation. We validate the superiority of our proposed method through experiments on several public datasets, the proposed method significantly enhances the self-supervised learning performance for downstream tasks, particularly in classification and object detection tasks.

Jack of all trades, master of one: domain-specific and domain-general contributions to perceptual expertise in visual comparison

Perceptual expertise is typically domain-specific and rarely generalises beyond an expert’s domain of experience. Forensic feature-comparison examiners outperform the norm in domain-specific visual comparison, but emerging research suggests that they show advantages on other similar tasks outside their domain of expertise. For example, fingerprint examiners not only outperform novices in fingerprint comparison, but also in face comparison. Yet, the extent to which their skills generalise is poorly understood. In this study, we investigated the generalisability of perceptual expertise amongst forensic examiners by comparing their performance to novices and other examiners within and outside their area of expertise. We recruited 85 experts from three forensic disciplines (face, fingerprint, and firearms) and asked them to complete four different visual comparison tasks: faces, fingerprints, firearms, and novel-objects. Examiners displayed domain-specific expertise: they outperformed novices and other examiners within their domain of visual comparison expertise. Yet, some of their skill also generalised: examiners also outperformed novices outside their area of expertise. However, while individual differences in examiners’ performance within their domain of experience were associated with their performance in a novel comparison task, they were not related to their performance on tasks outside their expert domain. These results provide key insight into the domain-specific and domain-general contributions of forensic examiners’ perceptual expertise. Forensic expertise lends some generalisable skill to other visual comparison tasks, but best performance is still seen within examiners’ domain of expertise.

Omnicare: A Comprehensive ML/DL-Based Prediction System for Healthcare and Agriculture

Effective decision-making in healthcare and agriculture can be challenging due to the complexity and volume of data involved. Traditional methods often require extensive manual analysis and domain-specific expertise, which can be time-consuming and prone to error. The challenge is compounded by the need for real-time insights and accurate predictions to address critical issues such as disease diagnosis and crop management. Omnicare tackles these challenges by using advanced machine learning and deep learning technologies to facilitate predictions. With pretrained models, it delivers precise insights for medical and agricultural needs, eliminating the need for user-provided training data. This streamlined, user-friendly approach enhances decision-making and represents a significant advancement in applying AI to real-world problems

Ontology extension by online clustering with large language model agents.

An ontology is a structured framework that categorizes entities, concepts, and relationships within a domain to facilitate shared understanding, and it is important in computational linguistics and knowledge representation. In this paper, we propose a novel framework to automatically extend an existing ontology from streaming data in a zero-shot manner. Specifically, the zero-shot ontology extension framework uses online and hierarchical clustering to integrate new knowledge into existing ontologies without substantial annotated data or domain-specific expertise. Focusing on the medical field, this approach leverages Large Language Models (LLMs) for two key tasks: Symptom Typing and Symptom Taxonomy among breast and bladder cancer survivors. Symptom Typing involves identifying and classifying medical symptoms from unstructured online patient forum data, while Symptom Taxonomy organizes and integrates these symptoms into an existing ontology. The combined use of online and hierarchical clustering enables real-time and structured categorization and integration of symptoms. The dual-phase model employs multiple LLMs to ensure accurate classification and seamless integration of new symptoms with minimal human oversight. The paper details the framework's development, experiments, quantitative analyses, and data visualizations, demonstrating its effectiveness in enhancing medical ontologies and advancing knowledge-based systems in healthcare.

Generative AI, Innovation, and Trust

Our paper explores the integration of generative artificial intelligence (GenAI) into organizations’ innovation and new product development processes, focusing on when and how to trust AI-generated outcomes in this context. We propose a framework to assess the level of trust required based on task-specific needs and the distinction between general and expert AI models. While inaccuracies in GenAI outputs can foster creativity during ideation, higher accuracy, and trust are essential for tasks requiring domain-specific expertise. The paper concludes by discussing the necessary human capabilities and organizational strategies for effectively deploying GenAI in innovation management.

The critical need for expert oversight of ChatGPT: Prompt engineering for safeguarding child healthcare information.

ChatGPT and other large language models have the potential to transform the health information landscape online. However, lack of domain-specific expertise and known errors in large language models raise concerns about the widespread adoption of content generated by these tools for parents making healthcare decisions for their children. The aim of this study is to determine if health-related text generated by ChatGPT under the supervision of an expert is comparable to that generated by an expert regarding persuasiveness and credibility from the perspective of a parent. In a cross-sectional study 116 parents aged 18-65 years (M = 45.02, SD = 10.92) were asked to complete a baseline assessment of their behavioral intentions regarding pediatric healthcare topics. Subsequently, participants were asked to rate text generated by either an expert or by ChatGPT under supervision of an expert. Results indicate that prompt engineered ChatGPT is capable of impacting behavioral intentions for medication, sleep, and diet decision-making. Additionally, there was little distinction between prompt engineered ChatGPT and content experts on perceived morality, trustworthiness, expertise, accuracy, and reliance. Notably, when differences were present, prompt engineered ChatGPT was rated as higher in trustworthiness and accuracy, and participants indicated they would be more likely to rely on the information presented by prompt engineered ChatGPT compared to the expert. Given that parents will trust and rely on information generated by ChatGPT, it is critically important that human domain-specific expertise be applied to healthcare information that will ultimately be presented to consumers (e.g., parents).

A critical review of large language models: Sensitivity, bias, and the path toward specialized AI

Abstract This paper examines the comparative effectiveness of a specialized compiled language model and a general-purpose model such as OpenAI’s GPT-3.5 in detecting sustainable development goals (SDGs) within text data. It presents a critical review of large language models (LLMs), addressing challenges related to bias and sensitivity. The necessity of specialized training for precise, unbiased analysis is underlined. A case study using a company descriptions data set offers insight into the differences between the GPT-3.5 model and the specialized SDG detection model. While GPT-3.5 boasts broader coverage, it may identify SDGs with limited relevance to the companies’ activities. In contrast, the specialized model zeroes in on highly pertinent SDGs. The importance of thoughtful model selection is emphasized, taking into account task requirements, cost, complexity, and transparency. Despite the versatility of LLMs, the use of specialized models is suggested for tasks demanding precision and accuracy. The study concludes by encouraging further research to find a balance between the capabilities of LLMs and the need for domain-specific expertise and interpretability.

A Comprehensive Framework for Pathology Classification Bridging Precision and Interpretability

Pathology classification is an indispensable component of medical diagnostics, facilitating accurate disease identification, prognosis determination, and treatment planning. However, the increasing complexity and heterogeneity of pathological manifestations pose significant challenges to traditional classification methodologies. This abstract presents a novel framework that integrates advanced machine learning techniques with domain-specific expertise to enhance the precision and interpretability of pathology classification. Our framework adopts a multi-modal approach, leveraging diverse data sources including histopathological images, clinical records, genomic profiles, and molecular biomarkers. Through feature fusion and dimensionality reduction techniques, we effectively capture intricate patterns and latent relationships embedded within the data, enabling robust classification across diverse pathological conditions. Furthermore, interpretability is prioritized through the incorporation of explainable AI methodologies, facilitating the identification of salient features and decision rationales underlying classification outcomes. This ensures transparency and trustworthiness in the diagnostic process, empowering clinicians to make informed decisions and refine treatment strategies. Validation of our framework across various pathological contexts demonstrates superior performance compared to conventional approaches, exhibiting high accuracy, sensitivity, and specificity. Moreover, its modular architecture facilitates customization and scalability, accommodating evolving diagnostic needs and emerging technological advancements. In conclusion, our proposed framework represents a significant advancement in pathology classification, offering a synergistic blend of computational sophistication and clinical relevance. By seamlessly integrating cutting-edge technologies with domain knowledge, it holds promise for revolutionizing diagnostic practices and improving patient outcomes in the realm of precision medicine.

Towards Reliable Healthcare LLM Agents: A Case Study for Pilgrims during Hajj

There is a pressing need for healthcare conversational agents with domain-specific expertise to ensure the provision of accurate and reliable information tailored to specific medical contexts. Moreover, there is a notable gap in research ensuring the credibility and trustworthiness of the information provided by these healthcare agents, particularly in critical scenarios such as medical emergencies. Pilgrims come from diverse cultural and linguistic backgrounds, often facing difficulties in accessing medical advice and information. Establishing an AI-powered multilingual chatbot can bridge this gap by providing readily available medical guidance and support, contributing to the well-being and safety of pilgrims. In this paper, we present a comprehensive methodology aimed at enhancing the reliability and efficacy of healthcare conversational agents, with a specific focus on addressing the needs of Hajj pilgrims. Our approach leverages domain-specific fine-tuning techniques on a large language model, alongside synthetic data augmentation strategies, to optimize performance in delivering contextually relevant healthcare information by introducing the HajjHealthQA dataset. Additionally, we employ a retrieval-augmented generation (RAG) module as a crucial component to validate uncertain generated responses, which improves model performance by 5%. Moreover, we train a secondary AI agent on a well-known health fact-checking dataset and use it to validate medical information in the generated responses. Our approach significantly elevates the chatbot’s accuracy, demonstrating its adaptability to a wide range of pilgrim queries. We evaluate the chatbot’s performance using quantitative and qualitative metrics, highlighting its proficiency in generating accurate responses and achieve competitive results compared to state-of-the-art models, in addition to mitigating the risk of misinformation and providing users with trustworthy health information.

BoNuS: Boundary Mining for Nuclei Segmentation With Partial Point Labels.

Nuclei segmentation is a fundamental prerequisite in the digital pathology workflow. The development of automated methods for nuclei segmentation enables quantitative analysis of the wide existence and large variances in nuclei morphometry in histopathology images. However, manual annotation of tens of thousands of nuclei is tedious and time-consuming, which requires significant amount of human effort and domain-specific expertise. To alleviate this problem, in this paper, we propose a weakly-supervised nuclei segmentation method that only requires partial point labels of nuclei. Specifically, we propose a novel boundary mining framework for nuclei segmentation, named BoNuS, which simultaneously learns nuclei interior and boundary information from the point labels. To achieve this goal, we propose a novel boundary mining loss, which guides the model to learn the boundary information by exploring the pairwise pixel affinity in a multiple-instance learning manner. Then, we consider a more challenging problem, i.e., partial point label, where we propose a nuclei detection module with curriculum learning to detect the missing nuclei with prior morphological knowledge. The proposed method is validated on three public datasets, MoNuSeg, CPM, and CoNIC datasets. Experimental results demonstrate the superior performance of our method to the state-of-the-art weakly-supervised nuclei segmentation methods. Code: https://github.com/hust-linyi/bonus.

Impact of AI-Driven Digital Twins in Industry 4.0: an Exploratory Analysis

Human society is witnessing a revolutionary growth of digital twin (DT) and artificial intelligence (AI) technologies, which has greater impact on Industry 4.0 revolution specially in academia and industry. DT is a digital representation of a physical entity, with data and infrastructure serving as its foundation, algorithms, and models as its core, and software and services as its application. The methodical and thorough integration of domain-specific expertise is even more essential to the foundations of DT and AI in industrial sectors. This paper provides a thorough analysis of more than 30 articles on AI-driven DT technologies employed in Industry 4.0 over the previous five years. It also describes the general advances of these technologies and the current status of AI integration in the domains of advanced robotics and smart manufacturing which are affecting human society. These include established methods like industrial automation as well as complex mechanism like 3D printing and human-robot collaboration. Additionally, the benefits of AI-powered DTs are explained in relation to sustainable development. The development potential and practical difficulties of AI-driven DTs are examined, with varying emphasis on various levels.

Multi-Modal Instruction-Tuning Small-Scale Language-and-Vision Assistant for Semiconductor Electron Micrograph Analysis

We present a novel framework for analyzing and interpreting electron microscopy images in semiconductor manufacturing using vision-language instruction tuning. The framework employs a unique teacher-student approach, leveraging pretrained multimodal large language models such as GPT-4 to generate instruction-following data for zero-shot visual question answering (VQA) and classification tasks, customizing smaller multimodal models (SMMs) for microscopy image analysis, resulting in an instruction tuned language-and-vision assistant. Our framework merges knowledge engineering with machine learning to integrate domain-specific expertise from larger to smaller multimodal models within this specialized field, greatly reducing the need for extensive human labeling. Our study presents a secure, cost-effective, and customizable approach for analyzing microscopy images, addressing the challenges of adopting proprietary models in semiconductor manufacturing.

Navigating the Power of Artificial Intelligence in Risk Management: A Comparative Analysis

This study presents a responsive analysis of the role of artificial intelligence (AI) in risk management, contrasting traditional approaches with those augmented by AI and highlighting the challenges and opportunities that emerge. AI, intense learning methodologies such as convolutional neural networks (CNNs), have been identified as pivotal in extracting meaningful insights from image data, a form of analysis that holds significant potential in identifying and managing risks across various industries. The research methodology involves a strategic selection and processing of images for analysis and introduces three case studies that serve as benchmarks for evaluation. These case studies showcase the application of AI, in place of image processing capabilities, to identify hazards, evaluate risks, and suggest control measures. The comparative evaluation focuses on the accuracy, relevance, and practicality of the AI-generated findings alongside the system’s response time and comprehensive understanding of the context. Results reveal that AI can significantly enhance risk assessment processes, offering rapid and detailed insights. However, the study also recognises the intrinsic limitations of AI in contextual interpretation, advocating for a synergy between technological and domain-specific expertise. The conclusion underscores the transformative potential of AI in risk management, supporting continued research to further integrate AI effectively into risk assessment frameworks.

Biomedical text readability after hypernym substitution with fine-tuned large language models.

The advent of patient access to complex medical information online has highlighted the need for simplification of biomedical text to improve patient understanding and engagement in taking ownership of their health. However, comprehension of biomedical text remains a difficult task due to the need for domain-specific expertise. We aimed to study the simplification of biomedical text via large language models (LLMs) commonly used for general natural language processing tasks involve text comprehension, summarization, generation, and prediction of new text from prompts. Specifically, we finetuned three variants of large language models to perform substitutions of complex words and word phrases in biomedical text with a related hypernym. The output of the text substitution process using LLMs was evaluated by comparing the pre- and post-substitution texts using four readability metrics and two measures of sentence complexity. A sample of 1,000 biomedical definitions in the National Library of Medicine's Unified Medical Language System (UMLS) was processed with three LLM approaches, and each showed an improvement in readability and sentence complexity after hypernym substitution. Readability scores were translated from a pre-processed collegiate reading level to a post-processed US high-school level. Comparison between the three LLMs showed that the GPT-J-6b approach had the best improvement in measures of sentence complexity. This study demonstrates the merit of hypernym substitution to improve readability of complex biomedical text for the public and highlights the use case for fine-tuning open-access large language models for biomedical natural language processing.

Leveraging the Potential of Large Language Models in Education Through Playful and Game-Based Learning

This perspective piece explores the transformative potential and associated challenges of large language models (LLMs) in education and how those challenges might be addressed utilizing playful and game-based learning. While providing many opportunities, the stochastic elements incorporated in how present LLMs process text, requires domain expertise for a critical evaluation and responsible use of the generated output. Yet, due to their low opportunity cost, LLMs in education may pose some risk of over-reliance, potentially and unintendedly limiting the development of such expertise. Education is thus faced with the challenge of preserving reliable expertise development while not losing out on emergent opportunities. To address this challenge, we first propose a playful approach focusing on skill practice and human judgment. Drawing from game-based learning research, we then go beyond this playful account by reflecting on the potential of well-designed games to foster a willingness to practice, and thus nurturing domain-specific expertise. We finally give some perspective on how a new pedagogy of learning with AI might utilize LLMs for learning by generating games and gamifying learning materials, leveraging the full potential of human-AI interaction in education.

Machine-learning-assisted performance improvements for multi-resonance thermally activated delayed fluorescence molecules.

With favorable colour purity, multi-resonance thermally activated delayed fluorescence (MR-TADF) molecules exhibit enormous potential in high-definition displays. Due to the relatively small chemical space of MR-TADF molecules, it is challenging to improve molecular performance through domain-specific expertise alone. To address this problem, we focused on optimizing the classic molecule, DABNA-1, using machine learning (ML). Molecular morphing operations were initially employed to generate the adjacent chemical space of DABNA-1. Subsequently, a machine learning model was trained with a limited database and used to predict the properties throughout the generated chemical space. It was confirmed that the top 100 molecules suggested by machine learning present excellent electronic structures, characterized by small reorganization energy and singlet-triplet energy gaps. Our results indicate that the improvement in electronic structures can be elucidated through the view of the molecular orbital (MO). The results also reveal that the top 5 molecules present weaker vibronic peaks of the emission spectrum, demonstrating higher colour purity when compared to DABNA-1. Notably, the M2 molecule presents a high RISC rate, indicating its promising future as a high-efficiency MR-TADF molecule. Our machine-learning-assisted approach facilitates the rapid optimization of classical molecules, addressing a crucial requirement within the organic optoelectronic materials community.

Innovations in Computational Approaches for Nonlinear Problems and Complex System Simulations

Nonlinear problem solving and complex system simulation have become critical issues in many fields of science. The development of novel computational methods is crucial to understanding these complex systems. In this abstract, we explore the dynamic landscape of computational techniques, focusing on their uses in simulating complex systems and tackling nonlinear challenges. Creating complex algorithms that can deal with nonlinearity, chaos, and emergent behaviours is where it's at. Tools for modelling and comprehending such complex systems are few, but machine learning, artificial intelligence, and evolutionary computation are at the forefront. The way problems are solved has been completely rethought because of their nonlinearity-tolerance and ability to operate in high-dimensional domains. In addition, novel opportunities have arisen due to the combination of classical mathematical models with computer methods. The behaviour and emergent features of complex systems are best understood by hybrid approaches that combine differential equations, agent-based modelling, and cellular automata. These techniques provide a fine-grained comprehension of component interactions, illuminating emergent events. Moreover, the advent of high-performance computing has substantially expanded the breadth and resolution of simulations. Scientists are now able to probe increasingly complex systems, shedding light on their dynamics and behaviours. Computational capacities have been vastly improved by parallel computing, distributed systems, and cloud computing infrastructures, allowing for the study of systems that were once thought to be intractable. Nonlinear issues and complex system simulations can benefit greatly from the combination of cutting-edge computational approaches with domain-specific expertise. This abstract is a testament to the expanding significance and potential of these computational approaches in understanding complex systems and opening up new frontiers for research and solving problems.

Human Posture Estimation: A Systematic Review on Force-Based Methods—Analyzing the Differences in Required Expertise and Result Benefits for Their Utilization

Force-based human posture estimation (FPE) provides a valuable alternative when camera-based human motion capturing is impractical. It offers new opportunities for sensor integration in smart products for patient monitoring, ergonomic optimization and sports science. Due to the interdisciplinary research on the topic, an overview of existing methods and the required expertise for their utilization is lacking. This paper presents a systematic review by the PRISMA 2020 review process. In total, 82 studies are selected (59 machine learning (ML)-based and 23 digital human model (DHM)-based posture estimation methods). The ML-based methods use input data from hardware sensors—mostly pressure mapping sensors—and trained ML models for estimating human posture. The ML-based human posture estimation algorithms mostly reach an accuracy above 90%. DHMs, which represent the structure and kinematics of the human body, adjust posture to minimize physical stress. The required expert knowledge for the utilization of these methods and their resulting benefits are analyzed and discussed. DHM-based methods have shown their general applicability without the need for application-specific training but require expertise in human physiology. ML-based methods can be used with less domain-specific expertise, but an application-specific training of these models is necessary.

F-SCP: An automatic prompt generation method for specific classes based on visual language pre-training models

The zero-shot classification performance of large-scale vision-language pre-training models (e.g., CLIP, BLIP and ALIGN) can be enhanced by incorporating a prompt (e.g., “a photo of a [CLASS]”) before the class words. Modifying the prompt slightly can have significant effect on the classification outcomes of these models. Thus, it is crucial to include an appropriate prompt tailored to the classes. However, manual prompt design is labor-intensive and necessitates domain-specific expertise. The CoOp (Context Optimization) converts hand-crafted prompt templates into learnable word vectors to automatically generate prompts, resulting in substantial improvements for CLIP. However, CoOp exhibited significant variation in classification performance across different classes. Although CoOp-CSC (Class-Specific Context) has a separate prompt for each class, only shows some advantages on fine-grained datasets. In this paper, we propose a novel automatic prompt generation method called F-SCP (Filter-based Specific Class Prompt), which distinguishes itself from the CoOp-UC (Unified Context) model and the CoOp-CSC model. Our approach focuses on prompt generation for low-accuracy classes and similar classes. We add the Filter and SCP modules to the prompt generation architecture. The Filter module selects the poorly classified classes, and then reproduce the prompts through the SCP (Specific Class Prompt) module to replace the prompts of specific classes. Experimental results on six multi-domain datasets shows the superiority of our approach over the state-of-the-art methods. Particularly, the improvement in accuracy for the specific classes mentioned above is significant. For instance, compared with CoOp-UC on the OxfordPets dataset, the low-accuracy classes, such as, Class21 and Class26, are improved by 18% and 12%, respectively.