Precision-Driven Product Recommendation Software: Unsupervised Models, Evaluated by GPT-4 LLM for Enhanced Recommender Systems

Roumeliotis, Konstantinos I.; Tselikas, Nikolaos D.; Nasiopoulos, Dimitrios K.

doi:10.3390/software3010004

Cited by 3 publications

(1 citation statement)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The GPT series, developed by OpenAI, includes iterations like GPT-2, GPT-3, and GPT-4, leveraging the Transformer architecture for efficient sequential data processing with long-range dependencies [37]. Trained on extensive internet text data, GPT models grasp intricate language representations through unsupervised learning.…”

Section: Large Language Models In Nlpmentioning

confidence: 99%

Next-Generation Spam Filtering: Comparative Fine-Tuning of LLMs, NLPs, and CNN Models for Email Spam Classification

Roumeliotis,

Tselikas,

Nasiopoulos

2024

Electronics

Self Cite

View full text Add to dashboard Cite

Spam emails and phishing attacks continue to pose significant challenges to email users worldwide, necessitating advanced techniques for their efficient detection and classification. In this paper, we address the persistent challenges of spam emails and phishing attacks by introducing a cutting-edge approach to email filtering. Our methodology revolves around harnessing the capabilities of advanced language models, particularly the state-of-the-art GPT-4 Large Language Model (LLM), along with BERT and RoBERTa Natural Language Processing (NLP) models. Through meticulous fine-tuning tailored for spam classification tasks, we aim to surpass the limitations of traditional spam detection systems, such as Convolutional Neural Networks (CNNs). Through an extensive literature review, experimentation, and evaluation, we demonstrate the effectiveness of our approach in accurately identifying spam and phishing emails while minimizing false positives. Our methodology showcases the potential of fine-tuning LLMs for specialized tasks like spam classification, offering enhanced protection against evolving spam and phishing attacks. This research contributes to the advancement of spam filtering techniques and lays the groundwork for robust email security systems in the face of increasingly sophisticated threats.

show abstract

Section: Large Language Models In Nlpmentioning

confidence: 99%

Next-Generation Spam Filtering: Comparative Fine-Tuning of LLMs, NLPs, and CNN Models for Email Spam Classification

Roumeliotis,

Tselikas,

Nasiopoulos

2024

Electronics

Self Cite

View full text Add to dashboard Cite

show abstract

Integrating Self-Attention Mechanisms For Contextually Relevant Information In Product Management

GUNDA,

Thirupathi Rao KOMATI

2024

IJCESEN

View full text Add to dashboard Cite

GPT-Product is an innovative AI solution that aims to transform product management and development by using sophisticated natural language processing (NLP) abilities. Building on Transformer architecture, frameworks like as BERT, GPT, and T5 have greatly enhanced AI applications, thereby allowing more efficient chatbots, and translation services, content generating tools, and so on. GPT-Product utilises the advanced GPT-3.5 architecture to provide full solutions for market evaluation, interpretation of client input, and automated content development. This enhances decision-making processes. This product utilises the self-attention mechanism of the Transformer model to provide precise and contextually appropriate information, enabling effective management of the product lifetime. GPT-Product uses deep learning to optimise processes, decrease time-to-market, and enhance product quality. It positions itself as an essential tool for firms striving to maintain competitiveness in a rapidly changing industry.

show abstract

Enabling Design of Secure IoT Systems with Trade-Off-Aware Architectural Tactics

Orellana,

Cereceda-Balic,

Solar

et al. 2024

Sensors

View full text Add to dashboard Cite

The increasing use of the Internet of Things (IoT) in homes and industry brings significant security and privacy challenges, while also considering trade-off for performance, energy consumption, and processing capabilities. Few explicit and specific guidelines exist to help architects in considering these trade-offs while designing secure IoT systems. This article proposes to address this situation by extending the well-known architectural tactics taxonomies with IoT-specific trade-offs; to preserving auditability, the trade-offs address the quality characteristics of the ISO 25010:2023 standard. The proposed technique and catalog are illustrated with the design of the Nunatak environmental monitoring system. The proposal was empirically validated with a controlled experiment, where a balanced mix of 12 novice and expert practitioners had to design a secure IoT Environmental Monitoring System; they used similar architectural tactics catalogs, with versus without trade-off information. Results suggest that having this information yield significant improvements in decision-making effectiveness (Precision) and usefulness (F1-Score), particularly benefiting less experienced designers. Wider adoption of trade-off-aware catalogs of architectural tactics will allow systematic, auditable design of secure IoT systems, and especially so by novice architects.

show abstract

Precision-Driven Product Recommendation Software: Unsupervised Models, Evaluated by GPT-4 LLM for Enhanced Recommender Systems

Cited by 3 publications

References 45 publications

Next-Generation Spam Filtering: Comparative Fine-Tuning of LLMs, NLPs, and CNN Models for Email Spam Classification

Next-Generation Spam Filtering: Comparative Fine-Tuning of LLMs, NLPs, and CNN Models for Email Spam Classification

Integrating Self-Attention Mechanisms For Contextually Relevant Information In Product Management

Enabling Design of Secure IoT Systems with Trade-Off-Aware Architectural Tactics

Contact Info

Product

Resources

About