Articles

The rapid development of artificial intelligence (AI), particularly large language models (LLMs), has generated both enthusiasm and concern regarding its role in society. While these systems demonstrate impressive technical capabilities, public acceptance is often hindered by perceptions of unpredictability, mistrust, and fears amplified by media narratives. One potential strategy to improve user acceptance is anthropomorphism, the attribution of human-like qualities to AI systems which can make interactions feel more natural and trustworthy. This paper investigates the attributes most conducive to anthropomorphism by conducting a structured review across psychology, human-robot interaction, communication studies, and business applications. The analysis identifies key traits such as emotional expressiveness, conversational coherence, adaptive social behavior, and role-based framing that enhance perceptions of AI as relatable and dependable. By synthesizing these insights, we propose a conceptual framework that highlights the psychological, social, and technical dimensions of anthropomorphism in AI. The findings provide guidance for designing AI systems that balance efficiency with user trust, thereby supporting more effective integration of AI into business, research, and everyday life.

Large language models (LLMs) have transformed natural language processing (NLP), demonstrating exceptional proficiency in tasks such as text generation, translation, and summarization. However, LLMs are prone to generating biased, inaccurate, or contextually irrelevant outputs, posing significant risks in high-stakes domains such as healthcare, legal reasoning, and engineering. This paper systematically investigates the role of prompt engineering as a solution to these challenges. By strategically designing inputs, prompt engineering enhances LLM performance, yielding more accurate, contextually relevant, and ethically aligned outputs. Advanced techniques, including chain-of-thought (CoT) prompting and retrieval augmented generation (RAG), are examined for their ability to improve reasoning capabilities, reduce errors, and mitigate bias. CoT prompting facilitates structured, stepwise reasoning, while RAG incorporates real-time data, ensuring output accuracy in rapidly evolving fields. In addition, we present a novel comparative perspective on these techniques, highlighting their distinct strengths and limitations across specialized applications such as healthcare diagnostics and scientific data extraction. The findings demonstrate that sophisticated prompt engineering significantly elevates the reliability and precision of LLM outputs, while addressing critical ethical concerns such as data privacy, bias, and hallucination. These insights underscore the necessity of advanced prompt design in optimizing LLMs for high-impact applications, ensuring both performance and ethical integrity.

Retrieval-augmented generation (RAG) systems promise grounded answers from large language models (LLMs), yet performance depends critically on how source documents are segmented before indexing. This study investigates how pre-index chunking strategies affect both retrieval accuracy and answer quality in domain-specific scenarios. We curated a corpus on software-as-a-service (SaaS) editorial content and constructed a high-quality evaluation dataset containing 2,419 question-answer (QA) pairs generated through automated prompting and quality control. We compared four chunking approaches, including fixed-size, structure-aware recursive, semantic, and LLM-based methods. Our evaluation protocol assessed retrieval through document localization, semantic similarity, and context relevance, while generation quality was evaluated using chain-of-thought (CoT) criteria driven by judgments from LLMs. Results demonstrate that recursive chunking consistently outperforms other approaches across all metrics. Smaller chunks improve document localization, while moderately larger chunks enhance semantic alignment and generation scores. LLM based chunking variants show competitive performance but do not exceed top recursive configurations on the dataset. These findings indicate that preserving document structure through recursive chunking is beneficial for practical RAG implementations, providing actionable guidance for chunk size selection while highlighting token-budget constraints in current long context models.

Conventional task-oriented chatbots frequently suffer from task incompletions and low user satisfaction when handling complex queries. This research intro duces the complexity aware cascade, an adaptive architecture that improves user service quality by dynamically matching query complexity with the appropri ate computational response. The system uses confidence and relevance scores to intelligently route requests through a sequence of a natural language under standing (NLU) model, a retrieval-augmented generation (RAG) pipeline, or a large language model (LLM). The tiered architecture was evaluated via a ran domized controlled trial (RCT) with 150 participants, measuring task success and user satisfaction. The full cascade achieved a 90% journey completion rate, representing a 92.3% improvement over baseline system and substantial gains in SERVQUAL-based service quality scores. The experiment was conducted in a domain-specific knowledge base (essential oils) with a convenience sam ple that does not represent the global population, and no real-time deployment or long-term cost analysis was performed. Accordingly, the findings should be interpreted as evidence of effectiveness in a limited setting rather than as directly scalable to all domains. Even with these limitations, this study provides arigorously tested blueprint for developing more robust and user-centric conversational AI systems.

While conventional optical character recognition (OCR) systems can digitize text, they struggle with diverse handwriting styles, noisy inputs, and unstructured layouts, limiting their effectiveness. This study proposes enhanced large language model whisperer (ELLMW), a vision–language framework for accurate text extraction (TE) from fully handwritten scripts. The methodology integrates advanced preprocessing (noise reduction, binarization, and skew correction), deep learning–based handwriting recognition convolutional neural network–long short-term memory (CNN–LSTM), and LLM-based post-correction to ensure context-aware and structurally coherent outputs. The system converts scanned images, portable document formats (PDFs), and irregularly formatted answer sheets into machine-readable text, while automatically correcting errors in spelling, grammar, and layout. Experimental evaluation on a curated dataset of handwritten examination answer scripts (HEAS) demonstrates that ELLMW achieves 97.8% accuracy, 1.04%-character error rate (CER), and 3.24%-word error rate, outperforming widely used OCR tools including Tesseract, EasyOCR, Google Cloud Vision (GCV), PaddleOCR, ABBYY FineReader, and Transym OCR. The results highlight the model’s robustness across varying handwriting styles, noisy backgrounds, and complex document structures.

Robotic process automation (RPA) has been deployed in a plethora of industries, including the banking and insurance sectors. However, the key challenge of handling unexpected situations manifests either as an inadequacy of programming (since all situations cannot possibly be foreseen) or incongruous inputs. In parallel, deep learning models, including large language models (LLMs) and visual language models (VLMs), have shown human-like cognitive capabilities in real-world tasks, germinating the field of agentic LLMs. However, their computational expense, slow inference times, and massive energy consumption impede large-scale usage. We propose a framework that combines the two approaches to enable expedient invocation of LLMs for handling exceptions and supervising RPA bots. It aims to minimize the need for human supervision by “meta” automation, while also reducing energy usage and processing time. The automation workflow is presented as a graph, and our pipeline uses the GraphRAG framework to analyze and fix errors. We demonstrate the potential of our pipeline through two real-world examples in the banking and insurance sectors, provide our GitHub repository for reproducibility, and conclude with future research directions.

The daily many rural citizens visit government offices to inquire about beneficiary services that support poor and illiterate citizens. However, without proper knowledge, many eligible citizens fail to benefit from these services. In the artificial intelligence (AI) era, AI-powered chatbots, such as AI agents, can provide valuable support to the villagers and provide them with complete information at their door step. In this paper, a proposed framework, using a chatbot, to reduce the communication gap between citizens and government officials to improve service delivery performance. This chatbot is developed by using a built large language model, python libraries, fast API, and mongodb data base. Our findings demonstrate the challenges of imbalanced data and suggest improvements for future implementations. The system enhances service delivery by automating eligibility checks and reducing office visit frequency by up to 60%.

Transcribing natural language to visualization (NL2VIS) has been investigated for years but still suffer from several fundamental limitations (e.g., feature selection). Although large language models (LLMs) are good candidates but they incur computation cost and hard to trace their made decisions. To alleviate this problem, we introduced an alternative information-theoretic framework that utilized mutual information (MI) to quantify the statistical relationship between utterances and database features. In our approach, kernel density estimation (KDE) and neural estimation techniques were utilized to estimate MI, and to optimize a diversity-promoting objective balancing feature relevance and redundancy. We also introduced the information coverage ratio (ICR) to quantify the amount of information content preserved in feature selection decisions. In our experiments, we found that the proposed approach improved information-theoretic metrics, with F1-score of 0.863 and an ICR of 0.891. We observed that these improvements did not come at the cost of traditional benchmarks: validity reached 88.9%, legality 85.2%, and chart-type accuracy 87.6%. Moreover, significance tests (p < 0.001) and large effect sizes (Cohen’s d > 0.8) further supported that these improvements were meaningful for feature selection. Thus, this study provides a mathematical framework for applications requiring analytical validity that extends beyond NL2VIS to other machine learning contexts.

This research paper explores the use of large language model Meta AI 3 (LLaMA 3) for automating the resume screening process. Traditional resume screening methods that rely on keyword searching and human review can be inefficient, biased, and fail to identify qualified candidates. LLaMA 3, trained on large-scale text datasets, has the potential to accurately analyze resumes by understanding context and semantic details beyond simple keyword matching.The study presents a system that converts resume PDFs to text, inputs the text along with the job description into the LLaMA 3 model, and generates a ranked list of candidates with reasoning for their job fit. This discusses the data preparation, model setup, and performance evaluation of this system. Results show LLaMA 3 can rapidly process batches of resumes while reducing human bias in the screening process. The system aims to streamline hiring by automating the initial resume screening stage to surface top candidates for further in-depth evaluation. Key benefits include improved accuracy in identifying relevant skills, reduced bias compared to human screeners, and significant time savings for recruiters. The paper also examines ethical considerations around using AI for hiring decisions. Overall, this work demonstrates the promising application of large language models (LLMs) like LLaMA 3 to transform and enhance resume screening practices.

Large language models (LLMs) have paved a way for geographic information system (GIS) that can solve spatial problems with minimal human intervention. However, current commercial LLM-based GIS solutions pose many limitations for researchers, such as proprietary APIs, high operational costs, and internet connectivity requirements, making them inaccessible in resource-constrained environments. To overcome this, this paper introduced the LLM-Geo framework with the DS-GeoAI platform, integrating the DeepSeek-Coder model (the open-source, lightweight version deepseek-coder-1.3b-base) running directly on Google Colab. This approach eliminates API dependence, thus reducing deployment costs, and ensures data independence and sovereignty. Despite having only 1.3 billion parameters, DeepSeek-Coder proved to be highly effective: generating accurate Python code for complex spatial analysis, achieving a success rate comparable to commercial solutions. After an automated debugging step, the system achieved 90% accuracy across three case studies. With its strong error- handling capabilities and intelligent sample data generation, DS-GeoAI proves highly adaptable to real-world challenges. Quantitative results showed a cost reduction of up to 99% compared to API-based solutions, while expanding access to advanced geo-AI technology for organizations with limited resources.

Large language models (LLMs) have demonstrated impressive capabilities in code generation; however, their high computational demands, privacy limitations, and challenges in edge deployment restrict their practical use in domain-specific applications. This study explores the effectiveness of parameter efficient fine-tuning for small language models (SLMs) with fewer than 3 billion parameters. We adopt a hybrid approach that combines low-rank adaptation (LoRA) and 4-bit quantization (QLoRA) to reduce fine-tuning costs while preserving semantic consistency. Experiments on the CodeAlpaca-20k dataset reveal that SLMs fine-tuned with this method outperform larger baseline models, including Phi-3 Mini 4K base, in ROUGE-L. Notably, applying our approach to the LLaMA 3 3B and Qwen2.5 3B models yielded performance improvements of 54% and 55%, respectively, over untuned counterparts. We evaluate models developed by major artificial intelligence (AI) providers Google (Gemma 2B), Meta (LLaMA 3 1B/3B), and Alibaba (Qwen2.5 1.5B/3B) and show that parameter-efficient fine-tuning enables them to serve as cost-effective, high-performing alternatives to larger LLMs. These findings highlight the potential of SLMs as scalable solutions for domain-specific software engineering tasks, supporting broader adoption and democratization of neural code synthesis.

The rise of hate and offensive content on social media platforms, such as Facebook and Twitter, has emerged as an escalating concern, especially in Vietnam. Consequently, detecting hate and offensive spans in Vietnamese text is an essential area of research. This study introduces ViHateOff, an advanced framework that combines a hated speech dictionary (HSD) automatically constructed from the Vietnamese hate and offensive spans (ViHOS) dataset with the pre-trained language models for Vietnamese (PhoBERT)-large language model to enhance the detection of offensive expressions. The framework functions through two primary modules. First, it constructs an HSD from the ViHOS dataset, which serves as a reference for identifying hate and offensive language in Vietnamese text. Second, the framework integrates the PhoBERT-large language model with HSD, enhancing the detection of harmful words in the input text. Experimental results demonstrate that the proposed framework significantly outperforms existing state-of-the-art (SOTA), achieving an F1-score of 0.8693 on the all spans subset and 0.8709 on the multiple-spans subset representing relative improvements of over 10% compared to the strongest baseline.

In this study, we present an end-to-end, big-data–driven framework for continuously enriching and fine-tuning large language models (LLMs) with the latest professional and scientific medical knowledge. Streaming updates from premier sources such as The New England Journal of Medicine (NEJM) are ingested via an Apache Kafka cluster for low-latency delivery and durably archived in a three-node Apache Hadoop (Hadoop distributed file system (HDFS)) system. Each new article is preprocessed into high dimensional embeddings and indexed in a Milvus vector database to enable sub-second semantic retrieval over millions of records. At query or batch time, our retrieval-augmented generation (RAG) module retrieves the top-k relevant embeddings from Milvus and injects them into prompts for DeepSeek-R1, GPT-4o-mini, and Llama 3, models which are hosted, fine tuned, and served via Ollama on an NVIDIA GeForce RTX 3050 Ti GPU for efficient inference and continual learning. The enriched outputs are seamlessly delivered to end users through a Telegram bot programmed in Python using the Telebot library, linking the RAG-enhanced LLMs to an intuitive chat interface. Our Kafka, HDFS, Milvus, RAG, LLM, or Telegram bot pipeline demonstrably improves factual accuracy and topical currency of AI-generated medical insights across clinical decision support, patient engagement and education, drug discovery and development, virtual health assistants, and mental health support, laying the groundwork for truly intelligent, responsive, and data-driven healthcare solutions.

Improving user experience in accessing information on organizational websites remains a challenge. Users often face complex navigation and multi step searches that slow information retrieval. This study introduces the real time intelligent virtual assistant (RIVA), which integrates large language models (LLMs) with the retrieval-augmented generation (RAG) framework to support real-time interaction with website content. The system was implemented on the Universitas Pendidikan Ganesha (Undiksha) website using a WordPress content management system (CMS) and developed following the design science research (DSR) approach, which includes six stages: problem identification, solution objectives, design and development, demonstration, evaluation, and communication. The retrieval-augmented generation assessment (RAGAS) evaluation indicated that the combined model of text-embedding-ada-002 and semantic chunking yielded the best results, with context precision=0.83, context recall=0.90, response relevancy=0.91, faithfulness=0.83, and answer correctness=0.85. User experience questionnaire (UEQ) testing performed well, particularly in the novelty and stimulation dimensions. These results demonstrate that RIVA can provide users with access to relevant and engaging information. As a result, future research will focus on improving retrieval and developing adaptive semantic chunking for structured and complex data.

In the evolving field of Spirulina cultivation, the integration of the internet of things (IoT) has facilitated the optimization of spirulina growth and significantly enhanced biomass yield in the culture medium. This study outlines a control open-pond system for Spirulina cultivation that employs generative artificial intelligence (AI) and edge computing within an IoT framework. This transformative approach maintains optimal conditions and automates tasks traditionally managed through labor-intensive manual processes. The system is designed to detect, acquire, and monitor basin data via electronic devices, which is then analyzed by a large language model (LLM) to generate precise, context-aware recommendations based on domain-specific knowledge. The final output comprises SMS notifications sent to the farm manager, containing the generated recommendations, which keep them informed and enable timely intervention when necessary. To ensure continued autonomous operation in case of connectivity loss, pre-trained TinyML models were integrated into the Raspberry Pi. These models display alarm signals to alert the farm owner to any irregularities, thereby maintaining system stability and performance. This system has substantially improved the growth rate, biomass yield, and nutrient content of Spirulina. The results highlight the potential of this system to transform Spirulina cultivation by offering an adaptable, autonomous solution.