Full Text Available
Note: Clicking the button above will open the full text document at the original institutional repository in a new window.
Comparative evaluation of conventional search architectures and large language model-based approaches
Thesis (MSc)--Stellenbosch University, 2026.
Saved in:
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis |
| Language: | English |
| Published: |
Stellenbosch : Stellenbosch University
2026
|
| Tags: |
No Tags, Be the first to tag this record!
|
| _version_ | 1867614048576602112 |
|---|---|
| access_status_str | Open Access |
| author | Molefe, Kgothatso Ishmael |
| author2 | Engelbrecht, Andries P. |
| author_browse | Engelbrecht, Andries P. Molefe, Kgothatso Ishmael |
| author_facet | Engelbrecht, Andries P. Molefe, Kgothatso Ishmael |
| author_sort | Molefe, Kgothatso Ishmael |
| collection | Thesis |
| dc_rights_str_mv | Stellenbosch University |
| description | Thesis (MSc)--Stellenbosch University, 2026. |
| format | Thesis |
| id | oai:scholar.sun.ac.za:10019.1/136172 |
| institution | Stellenbosch University (South Africa) |
| language | English |
| last_indexed | 2026-06-10T12:45:50.231Z |
| license_str | Other — see source repository |
| provenance_str_mv | Harvested via OAI-PMH from SUNScholar — Stellenbosch University Repository |
| publishDate | 2026 |
| publishDateRange | 2026 |
| publishDateSort | 2026 |
| publisher | Stellenbosch : Stellenbosch University |
| publisherStr | Stellenbosch : Stellenbosch University |
| record_format | dspace |
| source_str | SUNScholar — Stellenbosch University Repository |
| spelling | oai:scholar.sun.ac.za:10019.1/136172 Comparative evaluation of conventional search architectures and large language model-based approaches Molefe, Kgothatso Ishmael Engelbrecht, Andries P. Stellenbosch University. Faculty of Science. Dept. of Computer Science. Thesis (MSc)--Stellenbosch University, 2026. Molefe, K. I. 2026. Comparative evaluation of conventional search architectures and large language model-based approaches. Unpublished masters thesis. Stellenbosch: Stellenbosch University [online]. Available: https://scholar.sun.ac.za/items/c69404a0-06e2-43a4-bf13-b928cd2e44ed Search technologies are fundamental to how individuals and organisations access, interpret, and synthesise information. Conventional search engines such as Google and Bing rely on keyword-based indexing and symbolic ranking algorithms that provide transparency, verifiability, and computational efficiency. However, these systems often struggle to capture semantics, intent, and contextual nuance in more complex queries. In contrast, large language model (LLM)-based systems, including Gemini and chat generative pre-trained transformer (ChatGPT) with browsing, employ neural embeddings and generative reasoning to deliver contextualised and conversational outputs. While these advances enhance informational synthesis, they also introduce challenges such as hallucinations, opaque reasoning processes, and reduced efficiency. Hybrid models, exemplified by Google artificial intelligence overviews, attempt to bridge these paradigms by combining symbolic precision with generative flexibility. The purpose of this thesis is to conduct a quantitative comparative evaluation of conventional, hybrid, and LLM-based search systems. A dataset of user-centred queries was used to assess retrieval effectiveness, latency, and stability across factual, ambiguous, and informational categories. The findings highlight distinct trade-offs across systems. LLM-based search demonstrated the strongest performance in contextual reasoning and informational synthesis, but was limited by higher latency and variability. Conventional systems, while less accurate in complex queries, proved to be efficient and stable. Hybrid approaches offered the most balanced performance, integrating the efficiency of conventional search with the contextual depth of LLMs. This study concludes that hybrid systems, particularly Google AI Overviews, represent a promising pathway for advancing search technologies. By combining the reliability of conventional methods with the contextual intelligence of LLMs, they provide a more comprehensive foundation for addressing the diverse spectrum of modern search needs. Masters 2026-04-24T08:14:16Z 2026-04-24T08:14:16Z 2026-03 Thesis https://scholar.sun.ac.za/handle/10019.1/136172 en Stellenbosch University 88 pages application/pdf Stellenbosch : Stellenbosch University |
| spellingShingle | Molefe, Kgothatso Ishmael Comparative evaluation of conventional search architectures and large language model-based approaches |
| title | Comparative evaluation of conventional search architectures and large language model-based approaches |
| title_full | Comparative evaluation of conventional search architectures and large language model-based approaches |
| title_fullStr | Comparative evaluation of conventional search architectures and large language model-based approaches |
| title_full_unstemmed | Comparative evaluation of conventional search architectures and large language model-based approaches |
| title_short | Comparative evaluation of conventional search architectures and large language model-based approaches |
| title_sort | comparative evaluation of conventional search architectures and large language model based approaches |
| url | https://scholar.sun.ac.za/handle/10019.1/136172 |
| work_keys_str_mv | AT molefekgothatsoishmael comparativeevaluationofconventionalsearcharchitecturesandlargelanguagemodelbasedapproaches |