{"version":1,"type":"story","url":"https://digestai.news/story/researchers-propose-controlled-llm-workflow-for-evidencegrounded-risk","json":"https://digestai.news/story/researchers-propose-controlled-llm-workflow-for-evidencegrounded-risk.json","markdown":"https://digestai.news/story/researchers-propose-controlled-llm-workflow-for-evidencegrounded-risk.md","slug":"researchers-propose-controlled-llm-workflow-for-evidencegrounded-risk","headline":"Researchers propose controlled LLM workflow for evidence‑grounded risk score diagnosis","summary":"A new arXiv paper introduces a controlled workflow that guides large language models (LLMs) to explain differences in risk scores by referencing similar past transactions. The method links three components: a retrieval step that pulls relevant historical records, contrastive SHapley Additive exPlanations (SHAP) that highlight evidence, and a reference‑based LLM reasoning stage that produces a diagnosis, followed by deterministic validation to ensure consistency.\n\nThe authors evaluate the workflow on a test dataset and report that it yields diagnoses that are more consistent, better grounded in evidence, and more traceable than those generated by the same LLM when it operates without the structured guidance. The paper positions the approach as a way to improve transparency and accountability in automated risk‑scoring systems, which are widely used in finance and other regulated domains.","keyPoints":["Workflow combines reference retrieval, contrastive SHAP evidence, and reference‑based LLM reasoning","Deterministic validation added to enforce consistency and traceability","Experiments show higher evidence grounding and consistency versus unguided LLM output"],"whyItMatters":"More explainable risk‑score diagnostics can increase trust and regulatory compliance for AI‑driven financial decisions.","category":{"slug":"research","name":"Research","url":"https://digestai.news/category/research"},"entities":{"companies":[],"models":[],"people":[]},"firstPublishedAt":"2026-10-20T04:00:00Z","updatedAt":"2026-10-20T04:00:00Z","sourceCount":1,"hasPrimarySource":true,"sources":[{"outlet":"arXiv cs.AI","title":"A Controlled LLM Workflow for Evidence-Grounded Diagnosis of Risk Score Differences","url":"https://arxiv.org/abs/2610.23962","publishedAt":"2026-10-20T04:00:00Z","type":"primary","primary":true,"lead":true}],"sourceNotes":null,"discussions":[],"thread":null,"cite":{"text":"Digest AI, \"Researchers propose controlled LLM workflow for evidence‑grounded risk score diagnosis\", 20 October 2026, https://digestai.news/story/researchers-propose-controlled-llm-workflow-for-evidencegrounded-risk","publisher":"Digest AI","title":"Researchers propose controlled LLM workflow for evidence‑grounded risk score diagnosis","datePublished":"2026-10-20T04:00:00Z","url":"https://digestai.news/story/researchers-propose-controlled-llm-workflow-for-evidencegrounded-risk"},"generatedBy":"Written by Digest AI's editorial model from the linked sources; the sources are the record.","license":"Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse"}