A Controlled LLM Workflow for Evidence-Grounded Diagnosis of Risk Score Differences

arXiv:2610.23962v1 Announce Type: new Abstract: We propose a controlled Large Language Model (LLM) workflow for explaining risk score differences using similar historical transactions. The workflow combines reference retrieval and contrastive SHapley Additive exPlanations (SHAP) evidence with refere

arXiv cs.AIDienstag 06:00 · 20.10.1 Min. Lesezeit