3
Archived Theses
0
DOIs Assigned
0%
DOI Rate
Discipline
Performance evaluation of llm based chatbots with E2e method:LLama-8b,LLama-7b,Gemma-7b and mistral-7b
This study investigates the performance of large language models (LLMs) within the context of customer support chatbots by employing an end-to-end (E2E) evaluation framework. Specifically, it compares three prominent open-source models (Gemma-7B, Mistral-7B, Llama-7B and Llama-8B) based on their ability to comprehend and respond to user queries in a meaningful and accurate manner. The chatbot application under review was designed to provide assistance on an educational content platform and was tested using over 3000 curated question-answer pairs. The evaluation combines both semantic and lexical metrics, using cosine similarity to measure the alignment of model responses with expert-written answers, and ROUGE metrics to assess word-level accuracy. Additionally, the study incorporates prompt engineering techniques and analyses how models handle random or off-topic inputs, providing a comprehensive view of their reliability and contextual sensitivity. Results indicate that Gemma-7B and Llama-8B performs most consistently across all metrics, while Mistral-7B offers balanced outputs with occasional variance. Llama-7B, although structurally robust, struggled to deliver semantically aligned and contextually appropriate responses. Overall, the findings highlight the practical implications of model selection for real-world chatbot deployments and demonstrate the importance of multi-dimensional evaluation methods when assessing LLM performance in customer interaction settings.
Yeni bir saldırı tespit sistemi geliştirmek için yeni bir yöntem
After the increased use of digital devices connected to the Internet, which in turn leads to users sharing their personal information, the adoption of intergovernmental institutions, including civil ones, in their work of archiving, management, marketing, etc. . On networked distributed systems, security experts have made the focus of their efforts to provide the necessary cybersecurity, which is to prevent interference by unauthorized persons from gaining access to databases and to protect networks from malicious attacks that cause losses of funds or assets connected to digital networks. Network and in our research, we tried to address the problem of (DDoS) through machine learning technology, where the (Extra Trees Classifier) algorithm was used, which reduces the size of the input data with a low computational cost and low variance, and the Random Forest algorithm with a low bias to choose the best available results from the ExtraTreesClassifier and train The model using the (Dense Neural Network) for learning and testing (IDS) model achieved an accuracy of 99.85%.
Makine öğrenmeyi kullanarak ince iğne aspirasyon görüntülerinde meme kanseri tahmini
Breast cancer, with an estimated 1.5 million new cases per year, is a critical worldwide health problem owing to the disease's high fatality rate. It is also the most common cancer among women, accounting for 16% of all cancer cases in this demographic globally. Mammography is the most successful way for detecting breast cancer in its early stages, allowing for early intervention. Breast cancer may be detected in its early stages using ultrasound, magnetic resonance imaging, and computational tomography, albeit these methods are not as good in investigating and diagnosing these abnormalities as other ways This work aims to develop a methodology that is capable of identifying and classifying cancerous tumors using digital mammography images. In this way, the diagnostic work of these images, carried out by radiologist specialists, will be supported by the system to be developed through the methodology presented in this work. Therefore, with the proposed methodology, it was expected an increase in the agility and effectiveness of the diagnosis and, thus, to increase the chances of cure of the patients, since a rapid and effective diagnosis is of fundamental importance for the treatment of the disease.