Retrieval-augmented generation: СУЧАСНІ МЕТОДИ ПОКРАЩЕННЯ ЯКОСТІ ПОШУКУ В ГІБРИДНИХ
Abstract
Infineon is a global semiconductor manufacturer operating across several industries, including automotive, power systems, and IoT devices. As a market leader in multiple domains, the rapid and accurate identification of product malfunctions – along with effective root cause analysis – is essential to remain competitive and deliver high standards of product reliability. Failure Analysis (FA) plays a critical role in achieving these objectives. However, FA engineers are faced with vast amounts of information, including previous debugging procedures, product documentation, and other related data. In addition to managing this complex information landscape, engineers must possess deep domain knowledge and apply best practices, presenting considerable challenges for any individual. The emergence of Large Language Models (LLMs) as state-of-the-art tools for natural language processing tasks has opened up new opportunities to support FA engineers in their daily information retrieval efforts. A previous master thesis explored this potential by developing FA-Bot, an LLM-based chatbot system using Retrieval-Augmented Generation (RAG) – a technique that combines information retrieval with context-aware text generation. However, this system relied on foundational LLMs trained on general internet data. The impact of fine-tuning such models on domain-specific data within this context remains unexplored.To address this gap, the present thesis investigates a range of fine-tuning approaches…
Read the paper
Related studies
- Knowledge Management Perspective of Generative Artificial Intelligence
- Navigating Generative Artificial Intelligence Promises and Perils for Knowledge and Creative Work
- Characterizing the evolving research on enterprise content management
- Large language models and multimodal foundation models for precision oncology
- From Generative AI to Extended Reality: Multidisciplinary Perspectives on the Challenges, Opportunities, and Future of Educational Computing
- Generative Artificial Intelligence: A New Engine for Advancing Environmental Science and Engineering
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.