@inproceedings{gao-etal-2026-beyond-black,
    title = "Beyond Black-Box Interventions: Latent Probing for Faithful Retrieval-Augmented Generation",
    author = "Gao, Linfeng  and
      Zhang, Qinggang  and
      Bi, Baolong  and
      Zeng, Bo  and
      Yuan, Zheng  and
      Chen, Zerui  and
      Wei, Zhimin  and
      Liu, Shenghua  and
      Xu, Linlong  and
      Wang, Longyue  and
      Luo, Weihua  and
      Su, Jinsong",
    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.1499/",
    pages = "29981--30000",
    ISBN = "979-8-89176-395-1",
    abstract = "Retrieval-Augmented Generation (RAG) systems often fail to maintain contextual faithfulness, generating responses that conflict with the provided context. Existing methods attempt to improve faithfulness through external interventions, such as specialized prompting, decoding-based calibration, or preference optimization. However, since these approaches treat the LLM as a black box, they lack a reliable mechanism to assess how these conflicts occur. Consequently, they tend to be brittle, data-intensive, and agnostic to the model{'}s internal reasoning process. In this paper, we move beyond black-box interventions to analyze the model{'}s internal reasoning process. We discover that conflicting and aligned knowledge states are linearly separable in the model{'}s latent space, and contextual noise systematically increases the entropy of these representations. Based on these findings, we propose ProbeRAG, a novel framework for faithful RAG that operates in three stages: (i) fine-grained knowledge pruning to filter irrelevant context, (ii) latent conflict probing to identify hard conflicts in the model{'}s latent space, and (iii) conflict-aware attention to modulate attention heads toward faithful context integration. Extensive experiments demonstrate that ProbeRAG substantially improves both accuracy and contextual faithfulness. The related resources are available at https://github.com/XMUDeepLIT/ProbeRAG."
}