@inproceedings{tu-etal-2025-investigating,
    title = "Investigating Factuality in Long-Form Text Generation: The Roles of Self-Known and Self-Unknownan",
    author = "Tu, Lifu  and
      Meng, Rui  and
      Joty, Shafiq  and
      Zhou, Yingbo  and
      Yavuz, Semih",
    editor = "Noidea, Noidea",
    booktitle = "Proceedings of the 2nd Workshop on Uncertainty-Aware NLP (UncertaiNLP 2025)",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.uncertainlp-main.27/",
    pages = "322--336",
    ISBN = "979-8-89176-349-4",
    abstract = "Large language models (LLMs) have demonstrated strong capabilities in text understanding and generation. However, they often lack factuality, producing a mixture of true and false in- formation, especially in long-form generation. In this work, we investigates the factuality of long-form text generation across various large language models (LLMs), including GPT-4, Gemini-1.5-Pro, Claude-3-Opus, Llama-3-70B, and Mistral. Our analysis reveals that factuality tend to decline in later sentences of the generated text, accompanied by a rise in the number of unsupported claims. Furthermore, we explore the effectiveness of different evaluation settings to assess whether LLMs can accurately judge the correctness of their own outputs: Self- Known (the percentage of supported atomic claims, decomposed from LLM outputs, that the corresponding LLMs judge as correct) and Self-Unknown (the percentage of unsupported atomic claims that the corresponding LLMs judge as incorrect). The results indicate that even advanced models fail to achieve perfect Self-Known scores, while their Self-Unknown scores remain notably above zero, reflecting ongoing uncertainty in their self-assessments. Moreover, we find a correlation between higher Self-Known scores and improved factuality, while higher Self-Unknown scores are associated with lower factuality. Even without sig nificant changes in the models' self-judgment (Self-Known and Self-Unknown), the number of unsupported claims can increases, likely as an artifact of long-form generation. Additional Retrieval-Augmented Generation (RAG) experiments also show the limitations of current LLMs in long-form generation, and provide the more research is needed to improve factuality in long-form text generation."
}