{"slug": "rasc-retrieval-constrained-llm-adjudication-for-clinical-value-set-authoring", "title": "RASC+: Retrieval-Constrained LLM Adjudication for Clinical Value Set Authoring", "summary": "Researchers introduced RASC+, a retrieval-constrained LLM adjudication method for clinical value set authoring, achieving a candidate-pool recall of 0.730 on the RASC benchmark. Using GPT-5 as a constrained adjudicator, the method improved macro F1 scores to 0.549 on the full test split and 0.533 on held-out publishers, outperforming prior approaches while ensuring all codes originate from an auditable pool.", "body_md": "arXiv:2606.23992v1 Announce Type: new\nAbstract: Clinical value sets define the standardized terminology codes used in quality measurement, phenotyping, cohort construction, and clinical decision support. The recently introduced Retrieval-Augmented Set Completion (RASC) benchmark showed that direct zero-shot large language model (LLM) generation is poorly suited to this task: clinical code systems are large, version-controlled, and not reliably memorized by language models. We study a stage-wise alternative in which candidate-pool construction is optimized for recall and a constrained LLM adjudicator is optimized for candidate selection. On the full 3,744-value-set RASC test split, Qwen3-based retrieval with vocabulary-aware expansion and code-display rescue retrieval increases candidate-pool recall from the original RASC retrieval baseline of 0.553 to 0.730; on the held-out-publisher stratum, pool recall is 0.655. The higher-recall pool alone is not sufficient: applying the original SAPBert cross-encoder to this expanded pool gives full-test macro F1 of 0.287 and held-out-publisher macro F1 of 0.233. Replacing the stage-2 selector with blinded GPT-5 adjudication over the same pool increases full-test macro F1 to 0.549 and held-out-publisher macro F1 to 0.533. These results show that retrieval-constrained LLM adjudication can substantially improve value set completion while preserving the safety constraint that all returned codes must come from an auditable candidate pool.", "url": "https://wpnews.pro/news/rasc-retrieval-constrained-llm-adjudication-for-clinical-value-set-authoring", "canonical_source": "https://arxiv.org/abs/2606.23992", "published_at": "2026-06-24 04:00:00+00:00", "updated_at": "2026-06-24 04:15:55.401709+00:00", "lang": "en", "topics": ["large-language-models", "ai-research", "natural-language-processing"], "entities": ["RASC+", "RASC", "Qwen3", "SAPBert", "GPT-5"], "alternates": {"html": "https://wpnews.pro/news/rasc-retrieval-constrained-llm-adjudication-for-clinical-value-set-authoring", "markdown": "https://wpnews.pro/news/rasc-retrieval-constrained-llm-adjudication-for-clinical-value-set-authoring.md", "text": "https://wpnews.pro/news/rasc-retrieval-constrained-llm-adjudication-for-clinical-value-set-authoring.txt", "jsonld": "https://wpnews.pro/news/rasc-retrieval-constrained-llm-adjudication-for-clinical-value-set-authoring.jsonld"}}