Search results for: large language models (LLMS)

Authors: Haixu Yu, Wenhui Cao

Abstract:

Tailoring Large Language Models (LLMs) to perform legal reasoning has been a popular trend in the study of AI and law. Researchers have mainly employed two methods to unlock the potential of LLMs, namely by finetuning the LLMs to expand their knowledge of law and by restructuring the prompts (In-Context Learning) to optimize the LLMs’ understanding of the legal questions. Although claiming the finetuning and renovated prompting can make LLMs more competent in legal reasoning, most state-of-the-art studies show quite limited improvements of practicability. In this paper, drawing on the study of the complexity and low interpretability of legal texts, we propose a prompting strategy based on the Chain of Thought (CoT) method. Instead of merely instructing the LLM to reason “step by step”, the prompting strategy requires the tested LLM to identify the ambiguity in the questions as the first step and then allows the LLM to generate corresponding answers in line with different understandings of the identified terms as the following step. The proposed prompting strategy attempts to encourage LLMs to "interpret" the given text from various aspects. Experiments that require the LLMs to answer “case analysis” questions of bar examination with general LLMs such as GPT 4 and legal LLMs such as LawGPT show that the prompting strategy can improve LLMs’ ability to better understand complex legal texts.

Keywords: ambiguity-identification, prompt, large language model, legal text understanding

Procedia PDF Downloads 59

Authors: Gangmin Li, Fan Yang

Abstract:

Personalized recommendation is crucial for any recommendation system. One of the techniques for personalized recommendation is to identify the intention. Traditional user intention identification uses the user’s selection when facing multiple items. This modeling relies primarily on historical behaviour data resulting in challenges such as the cold start, unintended choice, and failure to capture intention when items are new. Motivated by recent advancements in Large Language Models (LLMs) like ChatGPT, we present an approach for user intention identification by embracing LLMs with Chain-of-Thought (CoT) prompting. We use the initial user profile as input to LLMs and design a collection of prompts to align the LLM's response through various recommendation tasks encompassing rating prediction, search and browse history, user clarification, etc. Our tests on real-world datasets demonstrate the improvements in recommendation by explicit user intention identification and, with that intention, merged into a user model.

Keywords: personalized recommendation, generative user modelling, user intention identification, large language models, chain-of-thought prompting

Procedia PDF Downloads 52

Authors: Yinheng Li

Abstract:

The remarkable advancements in large language models (LLMs) have brought about significant improvements in natural language processing tasks. This paper presents a comprehensive review of in-context learning techniques, focusing on different types of prompts, including discrete, continuous, few-shot, and zero-shot, and their impact on LLM performance. We explore various approaches to prompt design, such as manual design, optimization algorithms, and evaluation methods, to optimize LLM performance across diverse tasks. Our review covers key research studies in prompt engineering, discussing their methodologies and contributions to the field. We also delve into the challenges faced in evaluating prompt performance, given the absence of a single ”best” prompt and the importance of considering multiple metrics. In conclusion, the paper highlights the critical role of prompt design in harnessing the full potential of LLMs and provides insights into the combination of manual design, optimization techniques, and rigorous evaluation for more effective and efficient use of LLMs in various Natural Language Processing (NLP) tasks.

Keywords: in-context learning, prompt engineering, zero-shot learning, large language models

Procedia PDF Downloads 80

Authors: Sarra Hasni, Sami Faiz

Abstract:

In recent years, location prediction on social networks has gained significant attention, with short and unstructured texts like tweets posing additional challenges. Advanced geolocation models have been proposed, increasing the need to explain their predictions. In this paper, we provide explanations for a geolocation black-box model using LIME and SHAP, two state-of-the-art XAI (eXplainable Artificial Intelligence) methods. We extend our evaluations to Large Language Models (LLMs) as post hoc explainers for tweet geolocation. Our preliminary results show that LLMs outperform LIME and SHAP by generating more accurate explanations. Additionally, we demonstrate that prompts with examples and meta-prompts containing phonetic spelling rules improve the interpretability of these models, even with informal input data. This approach highlights the potential of advanced prompt engineering techniques to enhance the effectiveness of black-box models in geolocation tasks on social networks.

Keywords: large language model, post hoc explainer, prompt engineering, local explanation, tweet geolocation

Procedia PDF Downloads 24

Authors: Azita Ramezani, Ghazal Mashhadiagha, Bahareh Sanabakhsh

Abstract:

This study researches the combination of Random. Forest classifiers with large language models (LLMs) and natural language processing (NLP) to improve diagnostic accuracy in chest X-ray analysis using the Indiana University dataset. Utilizing advanced NLP techniques, the research preprocesses textual data from radiological reports to extract key features, which are then merged with image-derived data. This improved dataset is analyzed with Random Forest classifiers to predict specific clinical results, focusing on the identification of health issues and the estimation of case urgency. The findings reveal that the combination of NLP, LLMs, and machine learning not only increases diagnostic precision but also reliability, especially in quickly identifying critical conditions. Achieving an accuracy of 99.35%, the model shows significant advancements over conventional diagnostic techniques. The results emphasize the large potential of machine learning in medical imaging, suggesting that these technologies could greatly enhance clinician judgment and patient outcomes by offering quicker and more precise diagnostic approximations.

Keywords: natural language processing (NLP), large language models (LLMs), random forest classifier, chest x-ray analysis, medical imaging, diagnostic accuracy, indiana university dataset, machine learning in healthcare, predictive modeling, clinical decision support systems

Procedia PDF Downloads 42

Authors: Debarag Banerjee, Pooja Singh, Arjun Avadhanam, Saksham Srivastava

Abstract:

Autonomous conversational agents, i.e., chatbots, are becoming an increasingly common mechanism for enterprises to provide support to customers and partners. In order to rate chatbots, especially ones powered by Generative AI tools like Large Language Models (LLMs), we need to be able to accurately assess their performance. This is where chatbot benchmarking becomes important. In this paper, authors propose the use of a benchmark that they call the E2E (End to End) benchmark and show how the E2E benchmark can be used to evaluate the accuracy and usefulness of the answers provided by chatbots, especially ones powered by LLMs. The authors evaluate an example chatbot at different levels of sophistication based on both our E2E benchmark as well as other available metrics commonly used in the state of the art and observe that the proposed benchmark shows better results compared to others. In addition, while some metrics proved to be unpredictable, the metric associated with the E2E benchmark, which uses cosine similarity, performed well in evaluating chatbots. The performance of our best models shows that there are several benefits of using the cosine similarity score as a metric in the E2E benchmark.

Keywords: chatbot benchmarking, end-to-end (E2E) benchmarking, large language model, user centric evaluation.

Procedia PDF Downloads 65

Authors: Lu Song Ma Li Zhi

Abstract:

With the rapid advancement of artificial intelligence technology, large language models (LLMs) have become a milestone in the field of natural language processing, demonstrating remarkable capabilities in semantic understanding, intelligent question answering, and text generation. These models are gradually penetrating various industries, particularly showcasing significant application potential in the data analysis domain. However, retraining or fine-tuning these models requires substantial computational resources and ample downstream task datasets, which poses a significant challenge for many enterprises and research institutions. Without modifying the internal parameters of the large models, prompt engineering techniques can rapidly adapt these models to new domains. This paper proposes a prompt design strategy aimed at leveraging the capabilities of large language models to automate the generation of data analysis code. By carefully designing prompts, data analysis requirements can be described in natural language, which the large language model can then understand and convert into executable data analysis code, thereby greatly enhancing the efficiency and convenience of data analysis. This strategy not only lowers the threshold for using large models but also significantly improves the accuracy and efficiency of data analysis. Our approach includes requirements for the precision of natural language descriptions, coverage of diverse data analysis needs, and mechanisms for immediate feedback and adjustment. Experimental results show that with this prompt design strategy, large language models perform exceptionally well in multiple data analysis tasks, generating high-quality code and significantly shortening the data analysis cycle. This method provides an efficient and convenient tool for the data analysis field and demonstrates the enormous potential of large language models in practical applications.

Keywords: large language models, prompt design, data analysis, code generation

Procedia PDF Downloads 37

Authors: Genady Grabarnik, Serge Yaskolko

Abstract:

Generative Artificial Intelligence (AI) has significantly expanded its applicability with the incorporation of Large Language Models (LLMs) and become a technology with promise to automate some areas that were very difficult to automate before. The paper describes the introduction of generative Artificial Intelligence into Introductory Computer and Data Science courses and analysis of effect of such introduction. The generative Artificial Intelligence is incorporated in the educational process two-fold: For the instructors, we create templates of prompts for generation of tasks, and grading of the students work, including feedback on the submitted assignments. For the students, we introduce them to basic prompt engineering, which in turn will be used for generation of test cases based on description of the problems, generating code snippets for the single block complexity programming, and partitioning into such blocks of an average size complexity programming. The above-mentioned classes are run using Large Language Models, and feedback from instructors and students and courses’ outcomes are collected. The analysis shows statistically significant positive effect and preference of both stakeholders.

Keywords: introductory computer and data science education, generative AI, large language models, application of LLMS to computer and data science education

Procedia PDF Downloads 57

Authors: Dong Wu, Michael Grenn

Abstract:

Managing software projects effectively is crucial for meeting deadlines, ensuring quality, and managing resources well. Traditional methods often struggle with predicting project timelines accurately due to uncertain schedules and complex data. This study addresses these challenges by combining time prediction algorithms with Large Language Models (LLMs). It makes use of real-world software project data to construct and validate a model. The model takes detailed project progress data such as task completion dynamic, team Interaction and development metrics as its input and outputs predictions of project timelines. To evaluate the effectiveness of this model, a comprehensive methodology is employed, involving simulations and practical applications in a variety of real-world software project scenarios. This multifaceted evaluation strategy is designed to validate the model's significant role in enhancing forecast accuracy and elevating overall management efficiency, particularly in complex software project environments. The results indicate that the integration of time prediction algorithms with LLMs has the potential to optimize software project progress management. These quantitative results suggest the effectiveness of the method in practical applications. In conclusion, this study demonstrates that integrating time prediction algorithms with LLMs can significantly improve the predictive accuracy and efficiency of software project management. This offers an advanced project management tool for the industry, with the potential to improve operational efficiency, optimize resource allocation, and ensure timely project completion.

Keywords: software project management, time prediction algorithms, large language models (LLMS), forecast accuracy, project progress prediction

Procedia PDF Downloads 77

Authors: Nikita Katyal, Shaurya Uppal

Abstract:

This paper tackles the significant challenge of accurately classifying customers within a retailer’s customer base. Accurate classification is essential for developing targeted marketing strategies that effectively engage this important demographic. To address this issue, we propose a method that utilizes Large Language Models (LLMs). By employing LLMs, we analyze the metadata associated with product purchases derived from historical data to identify key product categories that act as distinguishing factors. These categories, such as baby food, eldercare products, or family-sized packages, offer valuable insights into the likely household composition of customers, including families with babies, families with kids/teenagers, families with pets, households caring for elders, or mixed households. We segment high-confidence customers into distinct categories by integrating historical purchase behavior with LLM-powered product classification. This paper asserts that life stage segmentation can significantly enhance e-commerce businesses’ ability to target the appropriate customers with tailored products and campaigns, thereby augmenting sales and improving customer retention. Additionally, the paper details the data sources, model architecture, and evaluation metrics employed for the segmentation task.

Keywords: LLMs, segmentation, product tags, fine-tuning, target segments, marketing communication

Procedia PDF Downloads 22

Authors: Andrey Khalov

Abstract:

The rapid proliferation of unstructured data in IT infrastructure management demands innovative approaches for extracting actionable knowledge. This paper presents a framework for ontology-based knowledge extraction that combines relational graph neural networks (R-GNN) with large language models (LLMs). The proposed method leverages the DOLCE framework as the foundational ontology, extending it with concepts from ITSMO for domain-specific applications in IT service management and outsourcing. A key component of this research is the use of transformer-based models, such as DeBERTa-v3-large, for automatic entity and relationship extraction from unstructured texts. Furthermore, the paper explores how transfer learning techniques can be applied to fine-tune large language models (LLaMA) for using to generate synthetic datasets to improve precision in BERT-based entity recognition and ontology alignment. The resulting IT Ontology (ITO) serves as a comprehensive knowledge base that integrates domain-specific insights from ITIL processes, enabling more efficient decision-making. Experimental results demonstrate significant improvements in knowledge extraction and relationship mapping, offering a cutting-edge solution for enhancing cognitive computing in IT service environments.

Keywords: ontology mapping, R-GNN, knowledge extraction, large language models, NER, knowlege graph

Procedia PDF Downloads 16

Authors: Kien Vu, Jien Min Soh, Mohamed Jahangir Abubacker, Piyawut Pattamanon, Soojin Lee, Suvro Banerjee

Abstract:

Recent advances in Generative Artificial Intelligence (GenAI), in particular Large Language Models (LLMs) have shown promise to disrupt multiple industries at scale. However, LLMs also present unique challenges, notably, these so-called "hallucination" which is the generation of outputs that are not grounded in the input data that hinders its adoption into production. Common practice to mitigate hallucination problem is utilizing Retrieval Agmented Generation (RAG) system to ground LLMs'response to ground truth. RAG converts the grounding documents into embeddings, retrieve the relevant parts with vector similarity between user's query and documents, then generates a response that is not only based on its pre-trained knowledge but also on the specific information from the retrieved documents. However, the RAG system is not suitable for tabular data and subsequent data analysis tasks due to multiple reasons such as information loss, data format, and retrieval mechanism. In this study, we have explored a novel methodology that combines planning-and-execution and code generation agents to enhance LLMs' data analysis capabilities. The approach enables LLMs to autonomously dissect a complex analytical task into simpler sub-tasks and requirements, then convert them into executable segments of code. In the final step, it generates the complete response from output of the executed code. When deployed beta version on DataSense, the property insight tool of PropertyGuru, the approach yielded promising results, as it was able to provide market insights and data visualization needs with high accuracy and extensive coverage by abstracting the complexities for real-estate agents and developers from non-programming background. In essence, the methodology not only refines the analytical process but also serves as a strategic tool for real estate professionals, aiding in market understanding and enhancement without the need for programming skills. The implication extends beyond immediate analytics, paving the way for a new era in the real estate industry characterized by efficiency and advanced data utilization.

Keywords: large language model, reasoning, planning and execution, code generation, natural language processing, prompt engineering, data analysis, real estate, data sense, PropertyGuru

Procedia PDF Downloads 86

Authors: Shashwat Mookherjee, Shruti Dutta

Abstract:

This study explores linguistic distinctions among American, Indian, and Irish English dialects and assesses various Language Models (LLMs) in their ability to generate British English translations from these dialects. Using cosine similarity analysis, the study measures the linguistic proximity between original British English translations and those produced by LLMs for each dialect. The findings reveal that Indian and Irish English translations maintain notably high similarity scores, suggesting strong linguistic alignment with British English. In contrast, American English exhibits slightly lower similarity, reflecting its distinct linguistic traits. Additionally, the choice of LLM significantly impacts translation quality, with Llama-2-70b consistently demonstrating superior performance. The study underscores the importance of selecting the right model for dialect translation, emphasizing the role of linguistic expertise and contextual understanding in achieving accurate translations.

Keywords: cross-dialect translation, language models, linguistic similarity, multilingual NLP

Procedia PDF Downloads 74

Authors: Min Gao

Abstract:

In the past year, the advent of large language models (LLMs) has brought about a revolution in the language service industry, making it possible to efficiently produce more satisfactory and higher-quality translations. This is groundbreaking news for commercial companies involved in language services since much of a translator's work can now be completed by machines. However, it may be bad news for universities that provide translation training programs. They need to confront the challenges posed by AI in education by reconsidering issues such as the reform of traditional teaching methods, the translation ethics of students, and the new demands of the job market for their graduates. This article is an exploratory study of these issues based on the author's experiences in translation teaching. The research combines methods in the form of questionnaires and interviews. The findings include: (1) students may lose their motivation to learn in the AI era, but this can be compensated for by encouragement from the lecturer; (2) Translation ethics are not a serious problem in schools, considering the strict policies and regulations in place; (3) The role of translators has evolved in the new era, necessitating a reform of the traditional teaching methods.

Keywords: job market of translation, large language model, translation ethics, translation training

Procedia PDF Downloads 66

Authors: Andrey Khalov

Abstract:

The rapid proliferation of unstructured data in IT infrastructure management demands innovative approaches for extracting actionable knowledge. This paper presents a framework for ontology-based knowledge extraction that combines relational graph neural networks (R-GNN) with large language models (LLMs). The proposed method leverages the DOLCE framework as the foundational ontology, extending it with concepts from ITSMO for domain-specific applications in IT service management and outsourcing. A key component of this research is the use of transformer-based models, such as DeBERTa-v3-large, for automatic entity and relationship extraction from unstructured texts. Furthermore, the paper explores how transfer learning techniques can be applied to fine-tune large language models (LLaMA) for using to generate synthetic datasets to improve precision in BERT-based entity recognition and ontology alignment. The resulting IT Ontology (ITO) serves as a comprehensive knowledge base that integrates domain-specific insights from ITIL processes, enabling more efficient decision-making. Experimental results demonstrate significant improvements in knowledge extraction and relationship mapping, offering a cutting-edge solution for enhancing cognitive computing in IT service environments.

Keywords: ontology expansion, synthetic dataset, transformer fine-tuning, concept extraction, DOLCE, BERT, taxonomy, LLM, NER

Procedia PDF Downloads 12

Authors: Yake Zhang, Peng Xu

Abstract:

The development of building energy models (BEM) required for architectural design and analysis is a time-consuming and complex process, demanding a deep understanding and proficient use of simulation software. To streamline the generation of complex building energy models, this study proposes an automated method for generating building energy models using a large language model and the BEM library aimed at improving the efficiency of model generation. This method leverages a large language model to parse user-specified requirements for target building models, extracting key features such as building location, window-to-wall ratio, and thermal performance of the building envelope. The BEM library is utilized to retrieve energy models that match the target building’s characteristics, serving as reference information for the large language model to enhance the accuracy and relevance of the generated model, allowing for the creation of a building energy model that adapts to the user’s modeling requirements. This study enables the automatic creation of building energy models based on natural language inputs, reducing the professional expertise required for model development while significantly decreasing the time and complexity of manual configuration. In summary, this study provides an efficient and intelligent solution for building energy analysis and simulation, demonstrating the potential of a large language model in the field of building simulation and performance modeling.

Keywords: artificial intelligence, building energy modelling, building simulation, large language model

Procedia PDF Downloads 25

Authors: Colin Schmidt, Adrien Lecossier, Pascal Crubleau, Philippe Blanchard, Simon Richir

Abstract:

Introduction:The widespread availability of artificial intelligence, exemplified by Generative Pre-trained Transformers (GPT) relying on large language models (LLM), has caused a seismic shift in the realm of knowledge. Everyone now has the capacity to swiftly learn how these models can either serve them well or not. Today, conversational AI like ChatGPT is grounded in neural transformer models, a significant advance in natural language processing facilitated by the emergence of renowned LLMs constructed using neural transformer architecture. Inventiveness of an LLM : OpenAI's GPT-3 stands as a premier LLM, capable of handling a broad spectrum of natural language processing tasks without requiring fine-tuning, reliably producing text that reads as if authored by humans. However, even with an understanding of how LLMs respond to questions asked, there may be lurking behind OpenAI’s seemingly endless responses an inventive model yet to be uncovered. There may be some unforeseen reasoning emerging from the interconnection of neural networks here. Just as a Soviet researcher in the 1940s questioned the existence of Common factors in inventions, enabling an Under standing of how and according to what principles humans create them, it is equally legitimate today to explore whether solutions provided by LLMs to complex problems also share common denominators. Theory of Inventive Problem Solving (TRIZ) : We will revisit some fundamentals of TRIZ and how Genrich ALTSHULLER was inspired by the idea that inventions and innovations are essential means to solve societal problems. It's crucial to note that traditional problem-solving methods often fall short in discovering innovative solutions. The design team is frequently hampered by psychological barriers stemming from confinement within a highly specialized knowledge domain that is difficult to question. We presume ChatGPT Utilizes TRIZ 40. Hence, the objective of this research is to decipher the inventive model of LLMs, particularly that of ChatGPT, through a comparative study. This will enhance the efficiency of sustainable innovation processes and shed light on how the construction of a solution to a complex problem was devised. Description of the Experimental Protocol : To confirm or reject our main hypothesis that is to determine whether ChatGPT uses TRIZ, we will follow a stringent protocol that we will detail, drawing on insights from a panel of two TRIZ experts. Conclusion and Future Directions : In this endeavor, we sought to comprehend how an LLM like GPT addresses complex challenges. Our goal was to analyze the inventive model of responses provided by an LLM, specifically ChatGPT, by comparing it to an existing standard model: TRIZ 40. Of course, problem solving is our main focus in our endeavours.

Keywords: artificial intelligence, Triz, ChatGPT, inventiveness, problem-solving

Procedia PDF Downloads 72

Authors: Claudia Martínez-Araneda, Mariella Gutiérrez, Pedro Gómez, Diego Maldonado, Alejandra Segura, Christian Vidal-Castro

Abstract:

The purpose of this document is to showcase the preliminary work in developing an EduChatbot-type tool and measuring the effects of its use aimed at providing effective feedback to students in programming courses. This bot, hereinafter referred to as tutorBot+, was constructed based on chatGPT and is tasked with assisting and delivering timely positive feedback to students in the field of computer science at the Universidad Católica de Concepción. The proposed working method consists of four stages: (1) Immersion in the domain of Large Language Models (LLMs), (2) Development of the tutorBot+ prototype and integration, (3) Experiment design, and (4) Intervention. The first stage involves a literature review on the use of artificial intelligence in education and the evaluation of intelligent tutors, as well as research on types of feedback for learning and the domain of chatGPT. The second stage encompasses the development of tutorBot+, and the final stage involves a quasi-experimental study with students from the Programming and Database labs, where the learning outcome involves the development of computational thinking skills, enabling the use and measurement of the tool's effects. The preliminary results of this work are promising, as a functional chatBot prototype has been developed in both conversational and non-conversational versions integrated into an open-source online judge and programming contest platform system. There is also an exploration of the possibility of generating a custom model based on a pre-trained one tailored to the domain of programming. This includes the integration of the created tool and the design of the experiment to measure its utility.

Keywords: assessment, chatGPT, learning strategies, LLMs, timely feedback

Procedia PDF Downloads 67

Authors: Zhengrong Wu, Haibo Yang

Abstract:

In the context of escalating global climate change and environmental degradation, the complexity and frequency of natural disasters are continually increasing. Confronted with an abundance of information regarding natural disasters, traditional knowledge graph construction methods, which heavily rely on grammatical rules and prior knowledge, demonstrate suboptimal performance in processing complex, multi-source disaster information. This study, drawing upon past natural disaster reports, disaster-related literature in both English and Chinese, and data from various disaster monitoring stations, constructs question-answer templates based on large language models. Utilizing the P-Tune method, the ChatGLM2-6B model is fine-tuned, leading to the development of a disaster knowledge graph based on large language models. This serves as a knowledge database support for disaster emergency response.

Keywords: large language model, knowledge graph, disaster, deep learning

Procedia PDF Downloads 54

Authors: Sahar Mobeen, Anam Rafique, Irum Baig

Abstract:

Acoustic echo cancellation in multichannel is a system identification application. In real time environment, signal changes very rapidly which required adaptive algorithms such as Least Mean Square (LMS), Leaky Least Mean Square (LLMS), Normalized Least Mean square (NLMS) and average (AFA) having high convergence rate and stable. LMS and NLMS are widely used adaptive algorithm due to less computational complexity and AFA used of its high convergence rate. This research is based on comparison of acoustic echo (generated in a room) cancellation thorough LMS, LLMS, NLMS, AFA and newly proposed average normalized leaky least mean square (ANLLMS) adaptive filters.

Keywords: LMS, LLMS, NLMS, AFA, ANLLMS

Procedia PDF Downloads 565

Authors: Evgeny Pyshkin, Maxim Mozgovoy, Vladislav Volkov

Abstract:

The paper follows a discourse on computer-assisted language learning. We examine problems of foreign language teaching and learning and introduce a metamodel that can be used to define learning models of language grammar structures in order to support teacher/student interaction. Special attention is paid to the concept of a virtual language lab. Our approach to language education assumes to encourage learners to experiment with a language and to learn by discovering patterns of grammatically correct structures created and managed by a language expert.

Keywords: computer-assisted instruction, language learning, natural language grammar models, HCI

Procedia PDF Downloads 517

Authors: Bowen Ding, Yihao Kuang

Abstract:

In recent years, large-scale pre-trained language models have achieved state-of-the-art performance on a variety of natural language processing tasks. The word vectors produced by these language models can be viewed as dense encoded presentations of natural language that in text form. However, it is unknown how much linguistic information is encoded and how. In this paper, we construct several corresponding probing tasks for multiple linguistic information to clarify the encoding capabilities of different language models and performed a visual display. We firstly obtain word presentations in vector form from different language models, including BERT, ELMo, RoBERTa and GPT. Classifiers with a small scale of parameters and unsupervised tasks are then applied on these word vectors to discriminate their capability to encode corresponding linguistic information. The constructed probe tasks contain both semantic and syntactic aspects. The semantic aspect includes the ability of the model to understand semantic entities such as numbers, time, and characters, and the grammatical aspect includes the ability of the language model to understand grammatical structures such as dependency relationships and reference relationships. We also compare encoding capabilities of different layers in the same language model to infer how linguistic information is encoded in the model.

Keywords: language models, probing task, text presentation, linguistic information

Procedia PDF Downloads 108

Authors: K. O'Malley

Abstract:

Background: The emergence and rapid evolution of large language models (LLMs) (i.e., models of generative artificial intelligence, or AI) has been unprecedented. ChatGPT is one of the most widely used LLM platforms. Using natural language processing technology, it generates customized responses to user prompts, enabling it to mimic human conversation. Responses are generated using predictive modeling of vast internet text and data swathes and are further refined and reinforced through user feedback. The popularity of LLMs is increasing, with a growing number of students utilizing these platforms for study and revision purposes. Notwithstanding its many novel applications, LLM technology is inherently susceptible to bias and error. This poses a significant challenge in the educational setting, where academic integrity may be undermined. This study aims to evaluate the performance of the latest iteration of ChatGPT (ChatGPT4.0) in standardized state medical licensing examinations. Methods: A considered search strategy was used to interrogate the PubMed electronic database. The keywords ‘ChatGPT’ AND ‘medical education’ OR ‘medical school’ OR ‘medical licensing exam’ were used to identify relevant literature. The search included all peer-reviewed literature published in the past five years. The search was limited to publications in the English language only. Eligibility was ascertained based on the study title and abstract and confirmed by consulting the full-text document. Data was extracted into a Microsoft Excel document for analysis. Results: The search yielded 345 publications that were screened. 225 original articles were identified, of which 11 met the pre-determined criteria for inclusion in a narrative synthesis. These studies included performance assessments in national medical licensing examinations from the United States, United Kingdom, Saudi Arabia, Poland, Taiwan, Japan and Germany. ChatGPT 4.0 achieved scores ranging from 67.1 to 88.6 percent. The mean score across all studies was 82.49 percent (SD= 5.95). In all studies, ChatGPT exceeded the threshold for a passing grade in the corresponding exam. Conclusion: The capabilities of ChatGPT in standardized academic assessment in medicine are robust. While this technology can potentially revolutionize higher education, it also presents several challenges with which educators have not had to contend before. The overall strong performance of ChatGPT, as outlined above, may lend itself to unfair use (such as the plagiarism of deliverable coursework) and pose unforeseen ethical challenges (arising from algorithmic bias). Conversely, it highlights potential pitfalls if users assume LLM-generated content to be entirely accurate. In the aforementioned studies, ChatGPT exhibits a margin of error between 11.4 and 32.9 percent, which resonates strongly with concerns regarding the quality and veracity of LLM-generated content. It is imperative to highlight these limitations, particularly to students in the early stages of their education who are less likely to possess the requisite insight or knowledge to recognize errors, inaccuracies or false information. Educators must inform themselves of these emerging challenges to effectively address them and mitigate potential disruption in academic fora.

Keywords: artificial intelligence, ChatGPT, generative ai, large language models, licensing exam, medical education, medicine, university

Procedia PDF Downloads 30

Authors: Yogendra Sisodia

Abstract:

Researchers are becoming more interested in extracting useful information from legal documents thanks to the development of large-scale language models in natural language processing (NLP), and deep learning has accelerated the creation of powerful text mining models. Legal fields like contracts benefit greatly from semantic text search since it makes it quick and easy to find related clauses. After collecting sentence embeddings, it is relatively simple to locate sentences with a comparable meaning throughout the entire legal corpus. The author of this research investigated two pre-trained language models for this task: MiniLM and Roberta, and further fine-tuned them on Legal Contracts. The author used Multiple Negative Ranking Loss for the creation of sentence transformers. The fine-tuned language models and sentence transformers showed promising results.

Keywords: legal contracts, multiple negative ranking loss, natural language inference, sentence transformers, semantic textual similarity

Procedia PDF Downloads 105

Authors: Liu Lin Xin

Abstract:

With the increasing complexity of systems, log parsing and anomaly detection have become crucial for maintaining system stability. However, traditional methods often struggle with adaptability and accuracy, especially when dealing with rapidly evolving log content and unfamiliar domains. To address these challenges, this paper proposes approach that integrates Retrieval Augmented Generation (RAG) technology with Prompt Engineering for Large Language Models, applied specifically in LogPrompt. This approach enables dynamic log parsing and intelligent anomaly detection by combining real-time information retrieval with prompt optimization. The proposed method significantly enhances the adaptability of log analysis and improves the interpretability of results. Experimental results on several public datasets demonstrate the method's superior performance, particularly in scenarios lacking training data, where it significantly outperforms traditional methods. This paper introduces a novel technical pathway for log parsing and anomaly detection, showcasing the substantial theoretical value and practical potential.

Keywords: log parsing, anomaly detection, RAG, prompt engineering, LLMs

Procedia PDF Downloads 31

Authors: Mourad Ben Bennani

Abstract:

Views of language and language learning have undergone a tremendous change over the last decades. Language is no longer seen as a set of structured rules. It is rather viewed as a tool of interaction and communication. This shift in views has resulted in change in viewing language learning, which gave birth to various approaches and methodologies of language teaching. Two of these approaches are content-based instruction and content and language integrated learning (CLIL). These are similar approaches which integrate content and foreign/second language learning through various methodologies and models as a result of different implementations around the world. This presentation deals with sociocultural view of CBI and CLIL. It also defines language and content as vital components of CBI and CLIL. Next it reviews the origins of CBI and the continuum perspectives and CLIL definitions and models featured in the literature. Finally it summarizes current aspects around research in program evaluation with a focus on the benefits and challenges of these innovative approaches for second language teaching.

Keywords: CBI, CLIL, CBI continuum, CLIL models

Procedia PDF Downloads 432

Authors: Brennan Lodge

Abstract:

Amidst a complex regulatory landscape, Retrieval Augmented Generation (RAG) emerges as a transformative tool for Governance Risk and Compliance (GRC) officers. This paper details the application of RAG in synthesizing Large Language Models (LLMs) with external knowledge bases, offering GRC professionals an advanced means to adapt to rapid changes in compliance requirements. While the development for standalone LLM’s (Large Language Models) is exciting, such models do have their downsides. LLM’s cannot easily expand or revise their memory, and they can’t straightforwardly provide insight into their predictions, and may produce “hallucinations.” Leveraging a pre-trained seq2seq transformer and a dense vector index of domain-specific data, this approach integrates real-time data retrieval into the generative process, enabling gap analysis and the dynamic generation of compliance and risk management content. We delve into the mechanics of RAG, focusing on its dual structure that pairs parametric knowledge contained within the transformer model with non-parametric data extracted from an updatable corpus. This hybrid model enhances decision-making through context-rich insights, drawing from the most current and relevant information, thereby enabling GRC officers to maintain a proactive compliance stance. Our methodology aligns with the latest advances in neural network fine-tuning, providing a granular, token-level application of retrieved information to inform and generate compliance narratives. By employing RAG, we exhibit a scalable solution that can adapt to novel regulatory challenges and cybersecurity threats, offering GRC officers a robust, predictive tool that augments their expertise. The granular application of RAG’s dual structure not only improves compliance and risk management protocols but also informs the development of compliance narratives with pinpoint accuracy. It underscores AI’s emerging role in strategic risk mitigation and proactive policy formation, positioning GRC officers to anticipate and navigate the complexities of regulatory evolution confidently.

Keywords: cybersecurity, gen AI, retrieval augmented generation, cybersecurity defense strategies

Procedia PDF Downloads 94

Authors: S. Gordon

Abstract:

Dual language immersion is growing fast in language teaching today. This study provides an overview and evaluation of the different models of Dual language immersion programs in US K-12 schools. First, the paper provides a brief current literature review on the theory of Dual Language Immersion (DLI) in Second Language Acquisition (SLA) studies. Second, examples of several types of DLI language teaching models in US K-12 public schools are presented (including 50/50 models, 90/10 models, etc.). Third, we focus on the unique example of DLI education in the state of Utah, a successful, growing program in K-12 schools that includes: French, Chinese, Spanish, and Portuguese. The project investigates the theory and practice particularly of the case of public elementary and secondary school children that study half their school day in the L1 and the other half in the chosen L2, from kindergarten (age 5-6) through high school (age 17-18). Finally, the project takes the observations of Utah French DLI elementary through secondary programs as a case study. To conclude, we look at the principal challenges, pedagogical objectives and outcomes, and important implications for other US states and other countries (such as France currently) that are in the process of developing similar language learning programs.

Keywords: dual language immersion, second language acquisition, language teaching, pedagogy, teaching, French

Procedia PDF Downloads 174

Authors: Clifford Irikefe Gbeyonron

Abstract:

Applied linguists concur that there is low-level achievement in English language use among Nigerian secondary school students. One of the factors that exacerbate this is classroom feature of which large class size is obvious. This study investigated the impact of large classes on learning English as a second language (ESL) at junior secondary school (JSS) in Yobe State. To achieve this, Solomon four-group experimental design was used. 382 subjects were divided into four groups and taught ESL for thirteen weeks. 356 subjects wrote the post-test. Data from the systematic observation and post-test were analyzed via chi square and ANOVA. Results indicated that learners in large classes (LLC) attain lower linguistic progress than learners in small classes (LSC). Furthermore, LSC have more chances to access teacher evaluation and participate actively in classroom discourse than LLC. In consequence, large classes have adverse effects on learning ESL in Yobe State. This is inimical to English language education given that each learner of ESL has their individual peculiarity within each class. It is recommended that strategies that prioritize individualization, grouping, use of language teaching aides, and theorization of innovative models in respect of large classes be considered.

Keywords: large classes, achievement, classroom discourse

Procedia PDF Downloads 408

Authors: Jamshid Qodirov, Sirojiddin Komolov, Ravilov Mirahmad, Olimjon Mirzayev

Abstract:

Nowadays, natural language processing tools play a crucial role in our daily lives, including various techniques with text processing. There are very advanced models in modern languages, such as English, Russian etc. But, in some languages, such as Uzbek, the NLP models have been developed recently. Thus, there are only a few NLP models in Uzbek language. Moreover, there is no such work that could show which Uzbek NLP model behaves in different situations and when to use them. This work tries to close this gap and compares the Uzbek NLP models existing as of the time this article was written. The authors try to compare the NLP models in two different scenarios: sentiment analysis and sentence similarity, which are the implementations of the two most common problems in the industry: classification and similarity. Another outcome from this work is two datasets for classification and sentence similarity in Uzbek language that we generated ourselves and can be useful in both industry and academia as well.

Keywords: NLP, benchmak, bert, vectorization

Procedia PDF Downloads 52