@inproceedings{si-etal-2026-faithlens,
    title = "{F}aith{L}ens: Detecting and Explaining Faithfulness Hallucination",
    author = "Si, Shuzheng  and
      Wang, Qingyi  and
      Zhao, Haozhe  and
      Bai, Yuzhuo  and
      Chen, Guanqiao  and
      Luo, Kangyang  and
      Chen, Gang  and
      Qi, Fanchao  and
      Zhang, Minjia  and
      Chang, Baobao  and
      Sun, Maosong",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.689/",
    pages = "14068--14099",
    ISBN = "979-8-89176-395-1",
    abstract = "Recognizing whether outputs from large language models (LLMs) contain faithfulness hallucination is crucial for real-world applications, e.g., retrieval-augmented generation and summarization. In this paper, we introduce FaithLens, a cost-efficient and effective faithfulness hallucination detection model that can jointly provide binary predictions and corresponding explanations to improve trustworthiness. To achieve this, we first synthesize training data with explanations via advanced LLMs and apply a well-defined data filtering strategy to ensure label correctness, explanation quality, and data diversity. Subsequently, we fine-tune the model on these well-curated training data as a cold start and further optimize it with rule-based reinforcement learning, using rewards for both prediction correctness and explanation quality. Results on 12 diverse tasks show that the 8B-parameter FaithLens outperforms advanced models such as GPT-5.2 and o3. Also, FaithLens can produce high-quality explanations, delivering a distinctive balance of trustworthiness, efficiency, and effectiveness."
}