返回全部动态
一种用于风险评分差异证据化诊断的受控LLM工作流
原标题:A Controlled LLM Workflow for Evidence-Grounded Diagnosis of Risk Score Differences
AI 摘要
该论文提出一种受控的大语言模型(LLM)工作流,用于借助相似历史交易解释风险评分差异。工作流结合参考检索、对比 SHAP 证据、基于参考的 LLM 推理和确定性验证。在测试数据集上的实验表明,相比没有结构化工作流引导的同一 LLM,该工作流能产生更一致、更有证据支撑且可追溯的诊断。
以上摘要由 AI 生成,可能存在误差。事实请以原文为准。
正文节选
A Controlled LLM Workflow for Evidence-Grounded Diagnosis of Risk Score Differences 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 reference-based LLM reasoning and deterministic validation. Experiments on a test dataset show that the workflow produces more consistent, evidence-grounded and
发布时间:2026-10-20 12:00
抓取时间:2026-10-20 12:10
来源机构:arXiv