{"ID":2855543,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.12137","arxiv_id":"2510.12137","title":"Credal Transformer: A Principled Approach for Quantifying and Mitigating Hallucinations in Large Language Models","abstract":"Large Language Models (LLMs) hallucinate, generating factually incorrect yet confident assertions. We argue this stems from the Transformer's Softmax function, which creates \"Artificial Certainty\" by collapsing ambiguous attention scores into a single probability distribution, discarding uncertainty information at each layer. To fix this, we introduce the Credal Transformer, which replaces standard attention with a Credal Attention Mechanism (CAM) based on evidential theory. CAM produces a \"credal set\" (a set of distributions) instead of a single attention vector, with the set's size directly measuring model uncertainty. We implement this by re-conceptualizing attention scores as evidence masses for a Dirichlet distribution: sufficient evidence recovers standard attention, while insufficient evidence yields a diffuse distribution, representing ambiguity. Empirically, the Credal Transformer identifies out-of-distribution inputs, quantifies ambiguity, and significantly reduces confident errors on unanswerable questions by abstaining. Our contribution is a new architecture to mitigate hallucinations and a design paradigm that integrates uncertainty quantification directly into the model, providing a foundation for more reliable AI.","short_abstract":"Large Language Models (LLMs) hallucinate, generating factually incorrect yet confident assertions. We argue this stems from the Transformer's Softmax function, which creates \"Artificial Certainty\" by collapsing ambiguous attention scores into a single probability distribution, discarding uncertainty information at each...","url_abs":"https://arxiv.org/abs/2510.12137","url_pdf":"https://arxiv.org/pdf/2510.12137v1","authors":"[\"Shihao Ji\",\"Zihui Song\",\"Jiajie Huang\"]","published":"2025-10-14T04:31:49Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cs.AI\"]","methods":"[\"Transformer\",\"Large Language Model\",\"Language Model\"]","has_code":false}