Large language model (LLM) hallucinations, meaning fluent but factually incorrect generations, fall into two types: faithfulness violations, where the model misuses provided context, and factuality violations, where answers reflect errors in internal knowledge. Proper mitigation depends on knowing which source drives each answer. We study contributive attribution, i.e. the classification of the dominant knowledge source behind each output, and show that a simple linear probe trained on hidden representations can reliably identify it. We introduce ATTRIWIKI, a selfsupervised pipeline that automatically generates labeled training data by prompting models to recall withheld entities from memory or read them from context without relying on knowledge conflicts. Probes trained on ATTRIWIKI achieve up to 0.96 Macro-F1 on Llama-3.1- 8B, Mistral-7B, and Qwen2.5-7B, transfer to SQuAD and WebQuestions with 0.92–0.99 accuracy, and generalize zero-shot to Tighidet et al. (2024)’s benchmark, outperforming their probe on conflicting settings without retraining.
Furthermore, attribution mismatches raise error
rates by up to 70%, though correct attribution
does not guarantee correct answers, pointing to
the need for broader detection frameworks.