DADang Anh-Hoang

Dang Anh-Hoang

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Dang Anh-Hoang has a total of 2 co-authors. Here are the top co-authors by number of shared publications:

  • Le-Minh Nguyen

    Division of Advanced Science and Technology, Japan Advanced Institute of Science and Technology, Nomi, Japan

    1 shared publication
  • Vu Tran

    Division of Advanced Science and Technology, Japan Advanced Institute of Science and Technology, Nomi, Japan

    1 shared publication

Latest Publications

  • Top Cited Papers
    Open Access

    Survey and analysis of hallucinations in large language models: attribution to prompting strategies or model behavior

    by Dang Anh-Hoang, Vu Tran, Le-Minh Nguyen

    Hallucination in Large Language Models (LLMs) refers to outputs that appear fluent and coherent but are factually incorrect, logically inconsistent, or entirely fabricated. As LLMs are increasingly deployed in education, healthcare, law, and scientific research, understanding and mitigating hallucinations has become critical. In this work, we present a comprehensive survey and empirical analysis of hallucination attribution in LLMs. Introducing a novel framework to determine whether a given hallucination stems from not optimize prompting or the model's intrinsic behavior. We evaluate state-of-the-art LLMs—including GPT-4, LLaMA 2, DeepSeek, and others—under various controlled prompting conditions, using established benchmarks (TruthfulQA, HallucinationEval) to judge factuality. Our attribution framework defines metrics for Prompt Sensitivity (PS) and Model Variability (MV), which together quantify the contribution of prompts vs. model-internal factors to hallucinations. Through extensive experiments and comparative analyses, we identify distinct patterns in hallucination occurrence, severity, and mitigation across models. Notably, structured prompt strategies such as chain-of-thought (CoT) prompting significantly reduce hallucinations in prompt-sensitive scenarios, though intrinsic model limitations persist in some cases. These findings contribute to a deeper understanding of LLM reliability and provide insights for prompt engineers, model developers, and AI practitioners. We further propose best practices and future directions to reduce hallucinations in both prompt design and model development pipelines.