A Digital Twin (DT) replicates objects, processes, or systems for real-time monitoring, simulation, and predictive maintenance. Recent advancements like Large Language Models (LLMs) have revolutionized traditional AI systems and offer immense potential when combined with DT in industrial applications such as railway defect inspection. Traditionally, this inspection requires extensive defect samples to identify patterns, but limited samples can lead to overfitting and poor performance on unseen defects. Integrating pre-trained LLMs into DT addresses this challenge by reducing the need for vast sample data. We introduce DefectTwin, which employs a multimodal and multi-model (M^2) LLM-based AI pipeline to analyze both seen and unseen visual defects in railways. This application enables a railway agent to perform expert-level defect analysis using consumer electronics (e.g., tablets). A multimodal processor ensures responses are in a consumable format, while an instant user feedback mechanism (instaUF) enhances Quality-of-Experience (QoE). The proposed M^2 LLM outperforms existing models, achieving high precision (0.76-0.93) across multimodal inputs including text, images, and videos of pre-trained defects, and demonstrates superior zero-shot generalizability for unseen defects. We also evaluate the latency, token count, and usefulness of responses generated by DefectTwin on consumer devices. To our knowledge, DefectTwin is the first LLM-integrated DT designed for railway defect inspection.

An SCR that is assessed as relevant to safety goes through extra scrutiny to maintain personnel safety at the nuclear station. The current method of SCR classification is a manual one that involves human evaluators to examine multiple SCRs every week. These records, which may be submitted by any employee, cover a broad spectrum of events and undergo management review to determine an appropriate reaction. If an SCR is deemed relevant to safety, it undergoes further examination by the Health and Safety department and is documented in a specialized database. The SCR database encompasses a range of occurrences, from equipment malfunctions and delays in material delivery to staff missing training sessions, making it cumbersome for the Health and Safety department to sift through each SCR to identify safety-related items before transferring pertinent details into their safety tracking system. The aim of this project is to develop a machine learning classifier to automatically differentiate between safety-related and non-safety-related SCRs. While this tool is not intended to supplant human assessment, it will serve as an additional layer of scrutiny and facilitate the swift review of safetyrelated SCRs by triggering a pipeline that copies all relevant data into the safety system for final human verification.

Ongoing advancements in Generative AI (GenAI) have boosted the potential of applying long-standing "learning-by-teaching" practices in the form of a teachable agent (TA). Despite the recognized roles and opportunities of TAs, less is known about how GenAI could create synergy or introduce challenges in TAs and how students perceived the application of GenAI in TAs. This study explored middle school students' perceived roles, benefits, and challenges of GenAI-powered TAs in an authentic mathematics classroom. Through classroom observation, focus-group interviews, and open-ended surveys of 108 sixth-grade students, we found that students expected the GenAI-powered TA to serve as a learning companion, facilitator, and collaborative problem-solver. Students also expressed the benefits and challenges of GenAI-powered TAs. This study provides implications for the design of educational AI and AI-assisted instruction.

In the rapidly evolving field of cybersecurity, the integration of flow-level and packet-level information for real-time intrusion detection remains a largely untapped area of research. This paper introduces "XG-NID," a novel framework that, to the best of our knowledge, is the first to fuse flow-level and packet-level data within a heterogeneous graph structure, offering a comprehensive analysis of network traffic. Leveraging a heterogeneous graph neural network (GNN) with graph-level classification, XG-NID uniquely enables real-time inference while effectively capturing the intricate relationships between flow and packet payload data. Unlike traditional GNN-based methodologies that predominantly analyze historical data, XG-NID is designed to accommodate the heterogeneous nature of network traffic, providing a robust and real-time defense mechanism. Our framework extends beyond mere classification; it integrates Large Language Models (LLMs) to generate detailed, human-readable explanations and suggest potential remedial actions, ensuring that the insights produced are both actionable and comprehensible. Additionally, we introduce a new set of flow features based on temporal information, further enhancing the contextual and explainable inferences provided by our model. To facilitate practical application and accessibility, we developed "GNN4ID," an open-source tool that enables the extraction and transformation of raw network traffic into the proposed heterogeneous graph structure, seamlessly integrating flow and packet-level data. Our comprehensive quantitative comparative analysis demonstrates that XG-NID achieves an F1 score of 97\% in multi-class classification, outperforming existing baseline and state-of-the-art methods. This sets a new standard in Network Intrusion Detection Systems by combining innovative data fusion with enhanced interpretability and real-time capabilities.

This paper explores the application of the Condorcet Jury theorem to the domain of sentiment analysis, specifically examining the performance of various large language models (LLMs) compared to simpler natural language processing (NLP) models. The theorem posits that a majority vote classifier should enhance predictive accuracy, provided that individual classifiers' decisions are independent. Our empirical study tests this theoretical framework by implementing a majority vote mechanism across different models, including advanced LLMs such as ChatGPT 4. Contrary to expectations, the results reveal only marginal improvements in performance when incorporating larger models, suggesting a lack of independence among them. This finding aligns with the hypothesis that despite their complexity, LLMs do not significantly outperform simpler models in reasoning tasks within sentiment analysis, showing the practical limits of model independence in the context of advanced NLP tasks.

This paper examines the application of ChatGPT, a large language model (LLM), for question-and-answer (Q&A) tasks in the highly specialized field of nuclear data. The primary focus is on evaluating ChatGPT's performance on a curated test dataset, comparing the outcomes of a standalone LLM with those generated through a Retrieval Augmented Generation (RAG) approach. LLMs, despite their recent advancements, are prone to generating incorrect or 'hallucinated' information, which is a significant limitation in applications requiring high accuracy and reliability. This study explores the potential of utilizing RAG in LLMs, a method that integrates external knowledge bases and sophisticated retrieval techniques to enhance the accuracy and relevance of generated outputs. In this context, the paper evaluates ChatGPT's ability to answer domain-specific questions, employing two methodologies: A) direct response from the LLM, and B) response from the LLM within a RAG framework. The effectiveness of these methods is assessed through a dual mechanism of human and LLM evaluation, scoring the responses for correctness and other metrics. The findings underscore the improvement in performance when incorporating a RAG pipeline in an LLM, particularly in generating more accurate and contextually appropriate responses for nuclear domain-specific queries. Additionally, the paper highlights alternative approaches to further refine and improve the quality of answers in such specialized domains.

Dual encoder architectures like CLIP models map two types of inputs into a shared embedding space and learn similarities between them. However, it is not understood how such models compare two inputs. Here, we address this research gap with two contributions. First, we derive a method to attribute predictions of any differentiable dual encoder onto feature-pair interactions between its inputs. Second, we apply our method to CLIP-type models and show that they learn fine-grained correspondences between parts of captions and regions in images. They match objects across input modes and also account for mismatches. However, this visual-linguistic grounding ability heavily varies between object classes, depends on the training data distribution, and largely improves after in-domain training. Using our method we can identify knowledge gaps about specific object classes in individual models and can monitor their improvement upon fine-tuning.

As humanity stands on the brink of a new era of technological innovation, the ability to rapidly transform creative ideas into protected intellectual property (IP) is more crucial than ever. However, the conventional processes for patent drafting are fraught with challenges, demanding a nuanced understanding of advanced field knowledge and technical concepts. Existing large language models (LLMs), while powerful, often fall short in this IP creation domain due to their lack of specialized knowledge and context-awareness necessary for generating technically accurate patent documents. To bridge this critical gap, we propose a groundbreaking framework for Knowledge Fine-Tuning (KFT) of LLMs, designed to endow AI with the ability to autonomously mine, understand, and apply domain-specific knowledge. Our model, PatentGPT leverages a unique combination of knowledge graph-based pre-training, domain-specific supervised fine-tuning (SFT), and reinforcement learning from human feedback (RLHF). Through extensive evaluation, PatentGPT has demonstrated outstanding performance, scoring up to approximately 400% higher in patent related benchmark tests compared to state-of-the-art models. By KFT method the model's capability to not only assist but also augment human creativity and innovation, our approach sets a new standard for AI-driven intellectual property generation, paving the way for more efficient and effective invention processes.

Large Language Models (LLMs) are reported to hold undesirable attestation bias on inference tasks: when asked to predict if a premise P entails a hypothesis H, instead of considering H's conditional truthfulness entailed by P, LLMs tend to use the out-of-context truth label of H as a fragile proxy. In this paper, we propose a pipeline that exploits this bias to do explicit inductive inference. Our pipeline uses an LLM to transform a premise into a set of attested alternatives, and then aggregate answers of the derived new entailment inquiries to support the original inference prediction. On a directional predicate entailment benchmark, we demonstrate that by applying this simple pipeline, we can improve the overall performance of LLMs on inference and substantially alleviate the impact of their attestation bias.

This paper presents a novel approach to epidemic surveillance, leveraging the power of Artificial Intelligence and Large Language Models (LLMs) for effective interpretation of unstructured big data sources, like the popular ProMED and WHO Disease Outbreak News. We explore several LLMs, evaluating their capabilities in extracting valuable epidemic information. We further enhance the capabilities of the LLMs using in-context learning, and test the performance of an ensemble model incorporating multiple open-source LLMs. The findings indicate that LLMs can significantly enhance the accuracy and timeliness of epidemic modelling and forecasting, offering a promising tool for managing future pandemic events.