The posting
High Level Description Generative AI and Large Language Models (LLMs) have rapidly changed the possibilities for searching, interpreting, and summarizing information. However, AI-based solutions do not necessarily outperform traditional information retrieval methods in all situations.
This thesis investigates and compares different approaches to retrieving relevant information from large amounts of unstructured text, including traditional text-based search, semantic search using embeddings, and LLM-based Retrieval-Augmented Generation (RAG).
The study aims to identify the strengths and limitations of each approach in terms of relevance, accuracy, efficiency, and cost, providing insights into when modern AI-based search methods offer added value over traditional solutions.
Project Description The student will develop and evaluate different information retrieval solutions using publicly available datasets containing unstructured text.
The project will involve implementing and comparing three approaches:
- Traditional text-based search – Using keyword-based retrieval techniques to identify relevant documents or passages.
- Semantic search – Using vector embeddings to retrieve information based on semantic similarity rather than exact keyword matches.
- LLM-based RAG – Combining information retrieval with a Large Language Model to generate answers grounded in retrieved content.
The approaches will be evaluated using a common set of questions and datasets to compare their performance in terms of retrieval relevance, answer accuracy, response time, and computational cost.
The study may also investigate how different amounts of retrieved context affect the quality of generated answers and the risk of incorrect or misleading information.
The expected outcome is a comparative evaluation that highlights the strengths, weaknesses, and practical trade-offs of each method, helping organizations determine when AI-based information retrieval provides meaningful benefits over traditional search solutions.
Who are we looking for?
- Bachelor/Master of Science in Computer Science/Engineering
- Graduation in June 2027
- Fluency in Swedish, both written and spoken
- Fluency in English, both written and spoken
Purpose The purpose of this thesis is to evaluate how traditional and AI-based information retrieval methods differ in their ability to retrieve relevant information and provide accurate answers from unstructured text.
The study will investigate the following research questions:
- How do traditional text-based search, semantic search, and LLM-based RAG compare in terms of relevance, accuracy, and efficiency?
- How does the amount of available context affect retrieval performance and answer quality?
- How frequently do the different methods produce incorrect or misleading results?
- Which approach provides the best balance between quality, response time, and cost?
- For which types of questions does an LLM-based solution provide measurable added value compared to traditional search? An Exciting Journey with Knightec Group Semcon and Knightec have joined forces as Knightec Group. Together, we are Northern Europe’s leading strategic partner in product and digital service development. With a unique combination of cross-functional expertise and a holistic business understanding, we help our clients realize their strategies – from idea to complete solution.
Practical Information This is a thesis position, located at our office in Sundsvall. Start date January or March 2027.
Please submit your application as soon as possible, but no later than 2026-11-30. If you have any questions, you are welcome to contact [email protected]. Note that due to GDPR, we only accept applications through our careers page.
