Publications

Search-Based Generation Techniques for Improving LLM Responses: A Comparative Study of Zero-shot and RAG on GPT-3.5 and GPT-4

Oct 2023 — KIICE 2023

Domestic Conferences & Theses

Authors

Joongmin Shin*, Jungun Lee

Abstract

A comparative study on zero-shot versus retrieval-augmented generation setups for GPT-3.5 and GPT-4. The analysis outlines reliability and practical implementation benefits of evidence-grounded generation.

Key Contribution

Comparative analysis of zero-shot vs. RAG for GPT models, demonstrating benefits of evidence-grounded generation.