Pınar Ersoy
Research Subjects
Pınar Ersoy has a total of 3 co-authors. Here are the top co-authors by number of shared publications:
- Mustafa Erşahin
Research and Development Department, Commencis Teknoloji, Istanbul, Trkiye
4 shared publications - Dorukhan Arslan1 shared publication
- Ece Ünal1 shared publication
Latest Publications
- 21 February 2026
- Published by Turkish Journal of Archaeological Sciences in Turkish Journal of Archaeological Sciences
GlyphTrack: Orman Örtüsü Altında Jeoglif İlişkili Anomalilerin Tespiti İçin Bütünleşik Bir İş Akışı
Bu makale, Brezilya’nın Acre eyaletinde yağmur ormanı örtüsü altında kalan Kolomb-öncesi jeoglif hendek ve setleriyle ilişkili mikrotopografik izlerin belirlenmesini desteklemek üzere geliştirilen GlyphTrack iş akışını sunar. Yaklaşım, hava Laser Imaging Detection and Ranging modeli (LiDAR) bulunmayan koşullarda küresel ölçekte erişilebilir verileri birleştirir: Global Ecosystem Dynamics Investigation (GEDI) ayak izi yükseklik ölçümleri, uydu tabanlı sayısal yükseklik modelleri ve bitki örtüsü göstergeleri. İlk aşamada, Digital Elevation Model (DEM) ile GEDI zemin geri dönüşü arasındaki yükseklik farkı, taç yüksekliği ve ağaç örtüsüyle modellenerek beklenen bitki kaynaklı yanlılık kestirilir; bu beklentiden sapmalar sağlam z-skoru ve yüzdelik temelli bir puanlama ile olası antropojenik mikro-izler olarak işaretlenir. İkinci aşamada, bilinen jeoglif konumları ve etiket belirsizliği dikkate alınarak, yükseklik, fosfor ve akarsu uzaklıklarına dayalı bir çevresel benzerlik modeli oluşturulur ve üç km × üç km karo düzeyinde öncelik haritası üretilir. Son aşamada iki çıktı birleştirilerek aday noktalar sıralanır ve uzman değerlendirmesine uygun bir kısa liste elde edilir. Yöntem, bilinen bir jeoglif üzerinde en yüksek puanlı GEDI ayak izinin yakalanabildiğini ve bölgesel modelin ayırt edici performans üretebildiğini göstermektedir.
- 21 February 2026
- Published by Turkish Journal of Archaeological Sciences in Turkish Journal of Archaeological Sciences
GlyphTrack: Orman Örtüsü Altında Jeoglif İlişkili Anomalilerin Tespiti İçin Bütünleşik Bir İş Akışı
Bu makale, Brezilya’nın Acre eyaletinde yağmur ormanı örtüsü altında kalan Kolomb-öncesi jeoglif hendek ve setleriyle ilişkili mikrotopografik izlerin belirlenmesini desteklemek üzere geliştirilen GlyphTrack iş akışını sunar. Yaklaşım, hava Laser Imaging Detection and Ranging modeli (LiDAR) bulunmayan koşullarda küresel ölçekte erişilebilir verileri birleştirir: Global Ecosystem Dynamics Investigation (GEDI) ayak izi yükseklik ölçümleri, uydu tabanlı sayısal yükseklik modelleri ve bitki örtüsü göstergeleri. İlk aşamada, Digital Elevation Model (DEM) ile GEDI zemin geri dönüşü arasındaki yükseklik farkı, taç yüksekliği ve ağaç örtüsüyle modellenerek beklenen bitki kaynaklı yanlılık kestirilir; bu beklentiden sapmalar sağlam z-skoru ve yüzdelik temelli bir puanlama ile olası antropojenik mikro-izler olarak işaretlenir. İkinci aşamada, bilinen jeoglif konumları ve etiket belirsizliği dikkate alınarak, yükseklik, fosfor ve akarsu uzaklıklarına dayalı bir çevresel benzerlik modeli oluşturulur ve üç km × üç km karo düzeyinde öncelik haritası üretilir. Son aşamada iki çıktı birleştirilerek aday noktalar sıralanır ve uzman değerlendirmesine uygun bir kısa liste elde edilir. Yöntem, bilinen bir jeoglif üzerinde en yüksek puanlı GEDI ayak izinin yakalanabildiğini ve bölgesel modelin ayırt edici performans üretebildiğini göstermektedir.
- 28 January 2026
- Published by Springer Nature
- p. 139-148
Protocol-Driven Agentic Integration of LLMs: A Multi-tool Use Case
- 28 January 2026
- Published by Springer Nature
- p. 139-148
Protocol-Driven Agentic Integration of LLMs: A Multi-tool Use Case
- Open Access
- 23 November 2025
- Published by Orclever Science and Research Group in The European Journal of Research and Development
- Vol. 5 (1) , 149-163
An Empirical Comparison of Claude, Llama, and Gemini for Aspect-Level Sentiment
Aspect-based sentiment analysis provides granular insights into customer feedback by identifying discrete aspects, such as features or topics, and assigning a corresponding sentiment to each. This study assesses three large language models, hereafter referred to as LLMs, namely Google Gemini 2.5 Flash-Lite, Anthropic Claude Sonnet-4 delivered through AWS Bedrock, and Meta LLaMA 3.3 70B delivered through AWS Bedrock, using a real-world multilingual corpus of 7,841 Turkish mobile banking app reviews from İşbank in Turkey. We employ a prompt-based tagging protocol to extract aspect–sentiment pairs from every review, and we compare accuracy, F1-score, inference cost, and latency. The results show that all three LLMs can execute multilingual aspect extraction and sentiment categorization without task-specific fine-tuning. Claude Sonnet-4 attains the highest F1 for aspect extraction and the highest sentiment accuracy, although it incurs a markedly higher inference cost. Gemini 2.5 Flash-Lite achieves competitive accuracy at a fraction of the price, making it well-suited for high-volume analytics. Meta LLaMA at the 70B scale accessed through AWS Bedrock exhibits intermediate performance with moderate cost and latency. We provide detailed performance tables and figures, along with best-practice guidance for enterprise deployment. AWS Bedrock enables the strategic selection of Claude and LLaMA 3.3 70B for multilingual sentiment analysis, offering valuable insights from app reviews within scale, accuracy, and budget constraints.
- 23 November 2025
- Published by Orclever Science and Research Group in The European Journal of Research and Development
- Vol. 5 (1) , 149-163
Open AccessAn Empirical Comparison of Claude, Llama, and Gemini for Aspect-Level Sentiment
Aspect-based sentiment analysis provides granular insights into customer feedback by identifying discrete aspects, such as features or topics, and assigning a corresponding sentiment to each. This study assesses three large language models, hereafter referred to as LLMs, namely Google Gemini 2.5 Flash-Lite, Anthropic Claude Sonnet-4 delivered through AWS Bedrock, and Meta LLaMA 3.3 70B delivered through AWS Bedrock, using a real-world multilingual corpus of 7,841 Turkish mobile banking app reviews from İşbank in Turkey. We employ a prompt-based tagging protocol to extract aspect–sentiment pairs from every review, and we compare accuracy, F1-score, inference cost, and latency. The results show that all three LLMs can execute multilingual aspect extraction and sentiment categorization without task-specific fine-tuning. Claude Sonnet-4 attains the highest F1 for aspect extraction and the highest sentiment accuracy, although it incurs a markedly higher inference cost. Gemini 2.5 Flash-Lite achieves competitive accuracy at a fraction of the price, making it well-suited for high-volume analytics. Meta LLaMA at the 70B scale accessed through AWS Bedrock exhibits intermediate performance with moderate cost and latency. We provide detailed performance tables and figures, along with best-practice guidance for enterprise deployment. AWS Bedrock enables the strategic selection of Claude and LLaMA 3.3 70B for multilingual sentiment analysis, offering valuable insights from app reviews within scale, accuracy, and budget constraints.
- Open Access
- 13 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 194185-194196
A Comparative Evaluation of RAG Architectures for Cross-Domain LLM Applications: Design, Implementation, and Assessment
Retrieval-Augmented Generation (RAG) pairs large language models with external search to constrain knowledge staleness and hallucination, a critical need in finance and e-commerce where numerical precision and regulatory auditability are non-negotiable. This study resembles four paradigms: sparse, dense, hybrid, and fusion retrieval, each realized as LangChain templates for cloud-hosted GPT-4o and on-premises LLaMA deployments. We embed a zero-shot baseline and assess every pipeline with the Retrieval-Augmented Generation Assessment (RAGAS) protocol, which scores faithfulness, relevancy, context quality, and latency without revealing proprietary gold data. Hybrid and fusion systems achieve the best combination of recall and faithfulness. Dense retrieval maximizes semantic coverage; sparse retrieval provides clearer, faster traceability. Each yields substantial gains over the baseline by anchoring profit metrics, compliance evidence, and pricing to audited documents. Although empirical evaluation primarily focuses on finance and e-commerce, the same blueprints and metrics can apply to healthcare, education, and legal technology. The domains in scope demand reasoning that is traceable, bias-aware, and up to date. This study, therefore, provides an auditable, production-ready framework for reliable RAG across knowledge-intensive settings.
- 13 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 194185-194196
Open AccessA Comparative Evaluation of RAG Architectures for Cross-Domain LLM Applications: Design, Implementation, and Assessment
Retrieval-Augmented Generation (RAG) pairs large language models with external search to constrain knowledge staleness and hallucination, a critical need in finance and e-commerce where numerical precision and regulatory auditability are non-negotiable. This study resembles four paradigms: sparse, dense, hybrid, and fusion retrieval, each realized as LangChain templates for cloud-hosted GPT-4o and on-premises LLaMA deployments. We embed a zero-shot baseline and assess every pipeline with the Retrieval-Augmented Generation Assessment (RAGAS) protocol, which scores faithfulness, relevancy, context quality, and latency without revealing proprietary gold data. Hybrid and fusion systems achieve the best combination of recall and faithfulness. Dense retrieval maximizes semantic coverage; sparse retrieval provides clearer, faster traceability. Each yields substantial gains over the baseline by anchoring profit metrics, compliance evidence, and pricing to audited documents. Although empirical evaluation primarily focuses on finance and e-commerce, the same blueprints and metrics can apply to healthcare, education, and legal technology. The domains in scope demand reasoning that is traceable, bias-aware, and up to date. This study, therefore, provides an auditable, production-ready framework for reliable RAG across knowledge-intensive settings.
- Open Access
- 31 May 2024
- Published by Orclever Science and Research Group in Orclever Proceedings of Research and Development
- Vol. 4 (1) , 52-58
Benchmarking Llama 3 70B for Code Generation: A Comprehensive Evaluation
This study benchmarks the capabilities of Llama 3 70B, a 70-billion parameter large language model (LLM), for code generation tasks. To effectively train and fine-tune this massive model, we integrate PyTorch Fully Sharded Data Parallel (FSDP) [1], [2] for distributed training and Quantized Low-Rank Adaptation (Q-LoRA) [7] for efficient fine-tuning. We address challenges associated with distributed training, including communication overhead and synchronization complexities, through optimization strategies like gradient accumulation, optimizer state sharding, and mixed precision training. Additionally, we employ advanced training techniques such as Curriculum Learning, Dynamic Batch Sizing, and Adaptive Optimization Algorithms to enhance model performance and training efficiency. Our primary focus is evaluating the performance of the fine-tuned Llama 3 70B model on two widely-recognized code generation benchmarks: HumanEval [8] and MBPP [9]. HumanEval assesses the model's ability to translate natural language problem descriptions into functionally correct code, while MBPP evaluates its proficiency in solving complex programming problems by generating accurate Python code. We present detailed performance results on these benchmarks, analyzing the model's strengths and limitations in various code generation scenarios. Furthermore, we compare the impact of our training and fine-tuning methodologies on scalability, memory efficiency, and training speed, demonstrating the feasibility and efficiency of our approach. This benchmark study offers valuable insights for researchers and practitioners exploring the application of LLMs for code generation. It provides a comprehensive evaluation of Llama 3 70B's capabilities, sheds light on the effectiveness of various training and fine-tuning techniques, and emphasizes the importance of rigorous benchmark evaluation in driving progress within this rapidly evolving field.
- 31 May 2024
- Published by Orclever Science and Research Group in Orclever Proceedings of Research and Development
- Vol. 4 (1) , 52-58
Open AccessBenchmarking Llama 3 70B for Code Generation: A Comprehensive Evaluation
This study benchmarks the capabilities of Llama 3 70B, a 70-billion parameter large language model (LLM), for code generation tasks. To effectively train and fine-tune this massive model, we integrate PyTorch Fully Sharded Data Parallel (FSDP) [1], [2] for distributed training and Quantized Low-Rank Adaptation (Q-LoRA) [7] for efficient fine-tuning. We address challenges associated with distributed training, including communication overhead and synchronization complexities, through optimization strategies like gradient accumulation, optimizer state sharding, and mixed precision training. Additionally, we employ advanced training techniques such as Curriculum Learning, Dynamic Batch Sizing, and Adaptive Optimization Algorithms to enhance model performance and training efficiency. Our primary focus is evaluating the performance of the fine-tuned Llama 3 70B model on two widely-recognized code generation benchmarks: HumanEval [8] and MBPP [9]. HumanEval assesses the model's ability to translate natural language problem descriptions into functionally correct code, while MBPP evaluates its proficiency in solving complex programming problems by generating accurate Python code. We present detailed performance results on these benchmarks, analyzing the model's strengths and limitations in various code generation scenarios. Furthermore, we compare the impact of our training and fine-tuning methodologies on scalability, memory efficiency, and training speed, demonstrating the feasibility and efficiency of our approach. This benchmark study offers valuable insights for researchers and practitioners exploring the application of LLMs for code generation. It provides a comprehensive evaluation of Llama 3 70B's capabilities, sheds light on the effectiveness of various training and fine-tuning techniques, and emphasizes the importance of rigorous benchmark evaluation in driving progress within this rapidly evolving field.