KR Labs at ArchEHR-QA 2025: A Verbatim Approach for Evidence-Based Question Answering

We present a lightweight, domain-agnostic verbatim pipeline for evidence-grounded question answering.Our pipeline operates in two steps: first, a sentence-level extractor flags relevant note sentences using either zero-shot LLM prompts or supervised ModernBERT classifiers.Next, an LLM drafts a questionspecific template, which is filled verbatim with sentences from the extraction step.This prevents hallucinations and ensures traceability.In the ArchEHR-QA 2025 shared task, our system scored 42.01%, ranking top-10 in core metrics and outperforming the organiser's 70B-parameter Llama-3.3 baseline.We publicly release our code and inference scripts under an MIT license.