@inproceedings{abdi-etal-2025-hallurag,
    title = "{H}allu{RAG}-{RUG} at {S}em{E}val-2025 Task 3: Using Retrieval-Augmented Generation for Hallucination Detection in Model Outputs",
    author = "Abdi, Silvana  and
      Hassani, Mahrokh  and
      Kinds, Rosalien  and
      Strijbis, Timo  and
      Terpstra, Roman",
    editor = "Rosenthal, Sara  and
      Ros{\'a}, Aiala  and
      Ghosh, Debanjan  and
      Zampieri, Marcos",
    booktitle = "Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/corrections-2025-08/2025.semeval-1.116/",
    pages = "846--851",
    ISBN = "979-8-89176-273-2",
    abstract = "Large Language Models (LLMs) suffer from a critical limitation: hallucinations, which refers to models generating fluent but factually incorrect text. This paper presents our approach to hallucination detection in English model outputs as part of the SemEval-2025 Task 3 (Mu-SHROOM). Our method, HalluRAG-RUG, integrates Retrieval-Augmented Generation (RAG) using Llama-3 and prediction models using token probabilities and semantic similarity. We retrieved relevant factual information using a named entity recognition (NER)-based Wikipedia search and applied abstractive summarization to refine the knowledge base. The hallucination detection pipeline then used this retrieved knowledge to identify inconsistent spans in model-generated text. This result was combined with the results of two systems which identified hallucinations based on token probabilities and low-similarity sentences. Our system placed 33rd out of 41, performing slightly below the `mark all' baseline but surpassing the `mark none' and `neural' baselines with an IoU of 0.3093 and a correlation of 0.0833."
}