AI Paper Atlas

Research map / Large language models / Alignment and preferences

Human-LLM Collaborative Feature Engineering for Tabular Data

Zhuoyan Li, Aditya Bansal, Jinzhao Li, Shishuang He, Zhuoran Lu, Mutian Zhang, Qin Liu, Yiwei Yang, Swati Jain, Ming Yin, Yunyao Li

ICLR 2026 · Large language models › Alignment and preferences · approach: LLM-as-judge and feedback data · 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
decouple LLM proposal from utility/uncertainty-based selection (BNN+UCB)LLM feature engineering · 13 classification datasets, MLPerror reduction vs best baseline: 7.24%Improved
same, with XGBoostLLM feature engineering · 13 classification datasets, XGBoosterror reduction vs best baseline: 9.02%Improved
add selectively elicited human preference feedback (ablation)Ours (w/o human) · 13 datasets, MLPerror reduction: 7.24% -> 8.96%Improved
add selectively elicited human preference feedback (ablation)Ours (w/o human) · 13 datasets, XGBoosterror reduction: 9.02% -> 11.23%Improved
add human feedback (ablation)Ours · diabetes and ai_usage (MLP/XGBoost)AUROC: diabetes XGB 85.2 -> 84.8; ai_usage MLP 68.5 -> 68.3Mixed
use LLM-based methods instead of OpenFE/AutoGluonfeature engineering · 13 datasetsAUROCImproved
swap backbone LLM to GPT-3.5-turboOurs · 13 datasets average, XGBoostAUROC: 86.5 vs OCTree 86.0No clear effect
use the proposed method instead of OCTree on proprietary datasetfeature engineering · conversion (MLP)AUROC: 91.1 -> 92.6 (w/o human)Improved
use algorithm-triggered human feedback instead of human-led controlhuman-LLM collaboration · flight user studyfinal performanceImproved
use algorithm-triggered feedback instead of self-reasoning queryhuman-LLM collaboration · flight user studycognitive load / completion time: p = 0.043 / p = 0.02Improved

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