🛰️ Daily AI Frontier
‹ back to 2026-09-17

EviGen: Predictive Evidence Scaffolding for Verifiable Clinical Rationale Generation

Research Medical/Healthcare AI

Ranking

Overall 78
Content 95
Popularity 39

Observed public metrics from 1 member.

Representative image for EviGen: Predictive Evidence Scaffolding for Verifiable Clinical Rationale Generation

Merged summary

TL;DR - EviGen is a three-layer framework that retrieves outcome-predictive evidence from longitudinal health records, uses it to scaffold clinical rationale generation, and verifies claims step by step. It improves predictive performance and rationale faithfulness while reducing omissions and hallucinations associated with full-context LLM and standard RAG approaches.

  • A patient-conditioned retriever uses learnable queries to identify evidence predictive of clinical outcomes, ranking spans by attribution scores rather than textual relevance alone.
  • An LLM generates clinical rationales grounded in the ranked evidence scaffold.
  • A process-supervised verifier evaluates individual reasoning steps and flags unreliable claims.
  • Across three medical prediction datasets, EviGen outperformed full-context LLM and RAG baselines and was preferred by clinical reviewers in a usability evaluation.

Sources (1)

EviGen: Predictive Evidence Scaffolding for Verifiable Clinical Rationale Generation

arXiv cs.CL Fengnan Li, Heman Burre, Liwen Sun, Roshni Varma, Matthew M. Engelhard 2026-09-16 arXiv:2609.18852
Public signals Semantic Scholar citations 0 · Semantic Scholar influential citations 0
Providers: Hugging Face · N/A OpenAlex · N/A Publisher · N/A Semantic Scholar · Citations 0 · Influential citations 0 X · N/A Fetched 2026-09-22 14:20:31.484679 UTC

TL;DR - EviGen is a three-layer framework that retrieves outcome-predictive evidence from longitudinal health records, uses it to scaffold clinical rationale generation, and verifies claims step by step. It improves predictive performance and rationale faithfulness while reducing omissions and hallucinations associated with full-context LLM and standard RAG approaches.

  • A patient-conditioned retriever uses learnable queries to identify evidence predictive of clinical outcomes, ranking spans by attribution scores rather than textual relevance alone.
  • An LLM generates clinical rationales grounded in the ranked evidence scaffold.
  • A process-supervised verifier evaluates individual reasoning steps and flags unreliable claims.
  • Across three medical prediction datasets, EviGen outperformed full-context LLM and RAG baselines and was preferred by clinical reviewers in a usability evaluation.
item →