AI Paper Atlas

Research map / Large language models / Retrieval and knowledge

Assessing Automated Fact-Checking for Medical LLM Responses with Knowledge Graphs

Shasha Zhou, Mingyu Huang, Jack Cole, Charles Britton, Ming Yin, Jan Wolber, Ke Li

AAAI 2026 · Large language models › Retrieval and knowledge · approach: Knowledge-augmented question answering · 2 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
use KG-based FAITH scoring instead of NLP and LLM-based metricsautomated factuality metric · MS-AKT, clinician judgments (16 questions, 20 clinicians)Pearson correlation with clinicians: BLEU-4 0.081 -> FAITH 0.696Improved
use FAITH to trigger Reject-to-Answer instead of model uncertaintyGPT-4o · MedQAaccuracyImproved
add KG-retrieval RAG triggered by FAITHGPT-4o · MedQAfactuality of justificationImproved
add multi-round conversation to claim extraction prompt (ablation)FAITH claim extractor · BioRED and DDI13recallImproved
add critical analysis prompt to claim extraction (ablation)FAITH claim extractor · BioRED and DDI13precisionImproved
replace GPT-4o extractor with Llama 3 or Llama 3.1 (ablation)FAITH claim extractor · BioRED and DDI13extraction performanceHurt
replace GPT-4o extractor with GPT-4o-mini (ablation)FAITH claim extractor · BioRED and DDI13extraction performanceNo clear effect
delete 20% of nodes or insert 20% noisy edges in UMLS (ablation)FAITH · UMLS perturbationperformanceHurt
delete 20% of random edges in UMLS (ablation)FAITH · UMLS perturbationperformanceNo clear effect
swap UMLS for PrimeKG or OGBL-biokg (ablation)FAITH · LLM rankingrelative ranking of LLMsNo clear effect

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