Benchmarking Hallucination Mitigation Techniques in Large Language Models: A Comparative Study
Global Social Science and Humanities Journal · 04.05.2026 · 4 (2) · 1-14
DOI: 10.59088/gi.v4i2.28 ↗Kurz gefasst
Fachartikel in der Zeitschrift Global Social Science and Humanities Journal, online erschienen am 04.05.2026. Verfasst von Wu Zhan und 1 weiteren Autor:innen.
Abstract (Originalsprache)
Hallucinations defined as factually incorrect or fabricated outputs remain a critical limitation of Large Language Models (LLMs), significantly undermining their reliability in high-stakes applications. This paper presents a systematic and reproducible comparative evaluation of prominent hallucination mitigation strategies, including prompt engineering, retrieval-augmented generation (RAG), and self-consistency decoding. Using benchmark factual question-answering datasets, we assess these approaches across multiple evaluation dimensions, including factual accuracy, hallucination rate, and response consistency. Furthermore, we introduce a unified evaluation protocol and extend prior work by incorporating a hybrid evaluation perspective that examines trade-offs between grounding effectiveness and computational overhead. Experimental results indicate that retrieval-based methods substantially improve factual grounding at the cost of increased latency, whereas prompt-based techniques provide lightweight yet less robust improvements. We complement quantitative findings with qualitative error analysis and discuss practical implications for real-world deployment. This study contributes a standardized benchmarking framework and provides actionable insights into optimizing reliability–efficiency trade-offs in LLM-based systems..
Zitieren
APA
Zhan, W., & Saif, A. (2026). Benchmarking Hallucination Mitigation Techniques in Large Language Models: A Comparative Study. Global Social Science and Humanities Journal, 4(2), 1-14. https://doi.org/10.59088/gi.v4i2.28
Vancouver
Zhan W, Saif A. Benchmarking Hallucination Mitigation Techniques in Large Language Models: A Comparative Study. Global Social Science and Humanities Journal. 2026;4(2):1-14. doi:10.59088/gi.v4i2.28
BibTeX
@article{Zhan2026,
author = {Zhan, Wu and Saif, Anwar},
title = {Benchmarking Hallucination Mitigation Techniques in Large Language Models: A Comparative Study},
journal = {Global Social Science and Humanities Journal},
year = {2026},
volume = {4},
number = {2},
pages = {1--14},
doi = {10.59088/gi.v4i2.28}
}
EUVIMED