AI Paper Atlas

Research map / Large language models / Agents, code and math

When the Domain Expert Has No Time and the LLM Developer Has No Clinical Expertise: Real-World Lessons from LLM Co-Design in a Safety-Net Hospital

Avni Kothari, Patrick Vossler, Jean Digitale, Mohammad Forouzannia, Elise Rosenberg, Michele Lee, Jenneé Bryant, Melanie Molina, James Marks, Lucas Zier, Jean Feng

AAAI 2026 · Large language models › Agents, code and math · approach: Agent instruction-following benchmarks · 4 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add tiered prompt refinement (onboarding docs, CFE feedback, ICL quotes) over the base attribute prompt (ablation)GPT-4o social needs extraction · LLM-judge concordance, overallconcordance: 0.77 -> 0.95Improved
add SW onboarding materials to attribute prompts (ablation)Prompt1 · LLM-judge concordance, overallconcordance: 0.77 -> 0.88Improved
add cross-functional expert feedback to prompts (ablation)Prompt2 · LLM-judge concordance, overallconcordance: 0.88 -> 0.91Improved
add ICL examples from previous SW notes and exclusion examples (ablation)Prompt3 · LLM-judge concordance, overallconcordance: 0.91 -> 0.95Improved
add CFE feedback to Outpatient Therapy prompt (ablation)Prompt2 · Outpatient Therapy concordanceconcordance: 0.72 -> 0.65Hurt
add CFE feedback to Safety prompt (ablation)Prompt2 · Safety concordanceconcordance: 0.92 -> 0.84Hurt
tiered prompt refinement on Food Insecurity attribute (ablation)Prompt1 · Food Insecurity concordanceconcordance: 1.00 -> 0.99No clear effect
tiered prompt refinement on Reason for Consult attribute (ablation)Prompt1 · Reason for Consult concordanceconcordance: 0.54 -> 0.92Improved
tiered prompt refinement on Outpatient Therapy attribute (ablation)Prompt1 · Outpatient Therapy concordanceconcordance: 0.51 -> 0.90Improved
use LLM-as-a-judge as proxy for human validation of prompt clarityReason for Consult and Patient Contacts · Human validationagreement with annotators: LLM app 0.65 (Reason for Consult), 0.72 (Patient Contacts)Mixed
decompose free-form summary into 15 structured attributespre-chart summarization · Human validation overallagreement with annotators: 0.89 LLM app vs 0.89 inter-annotatorImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy