AI Paper Atlas

Research map / Large language models / Retrieval and knowledge

Enhancing Predictive Model Learning via Domain-Knowledge Augmented Latent Feature Mining

Bingxuan Li, Pengyi Shi, Amy R Ward

AAAI 2026 · Large language models › Retrieval and knowledge · approach: Knowledge graph reasoning with LLMs · 0 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 FLAME-inferred latent features to gradient boosted treesGBT classifier · Incarceration diversion outcome predictionROC AUC: 84% -> 92%Improved
add FLAME-inferred latent features to logistic regressionLR classifier · Incarceration diversion outcome predictionROC AUC: 70% -> 85%Improved
add FLAME-inferred latent features to MLPMLP classifier · Incarceration diversion outcome predictionROC AUC: 81% -> 88%Improved
add FLAME-inferred latent features to random forestsRF classifier · Incarceration diversion outcome predictionF1: 70% -> 75%Improved
add FLAME-inferred social support feature to logistic regressionLR classifier · MIMIC discharge location predictionROC AUC: 65.22% -> 71.22%Improved
add FLAME-inferred social support feature to MLPMLP classifier · MIMIC discharge location predictionROC AUC: 63.19% -> 74.40%Improved
add FLAME-inferred social support feature to GBTGBT classifier · MIMIC discharge location predictionF1: 65.09% -> 75.38%Improved
use fine-tuned GPT-3.5 (FLAME g) instead of tabular ML models to infer risk levellatent feature inference · Risk level inferenceaccuracy: 58.24% -> 77.01%Improved
use LLaMA2 instead of GPT-3.5 as FLAME base modelFLAME latent feature inference · Risk level inferenceaccuracy: 77.01% -> 63.08%Hurt
add expert-provided socio-economic zip code information to the prompt (ablation)FLAME latent feature extraction · Incarceration diversion outcome predictionfeature extraction qualityImproved
replace external socio-economic data with GPT-4 internal knowledge of zip codes (ablation)FLAME domain knowledge · 50 zip codesaccuracy of generated context: 33 of 50 accurate, 17 hallucinated, 5 undeterminedHurt

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