# Marginal Response Surface Elicitation for Zero-Label Tabular Learning

arXiv: https://arxiv.org/abs/2609.39639 · HTML: https://mlsanity.com/paper/2609.39639/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 40 references that are in the map.
- First posted on arXiv 30 Sep 2026.

## Builds on (most cited first, 20 of 20)

- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [Deep Neural Networks and Tabular Data: A Survey](https://mlsanity.com/paper/2110.01889/) (2021)
- [TabLLM: Few-shot Classification of Tabular Data with Large Language Models](https://mlsanity.com/paper/2210.10723/) (2022)
- [TabArena: A Living Benchmark for Machine Learning on Tabular Data](https://mlsanity.com/paper/2506.16791/) (2025)
- [SCARF: Self-Supervised Contrastive Learning using Random Feature Corruption](https://mlsanity.com/paper/2106.15147/) (2021)
- [TabICLv2: A better, faster, scalable, and open tabular foundation model](https://mlsanity.com/paper/2602.11139/) (2026)
- [TabM: Advancing Tabular Deep Learning with Parameter-Efficient Ensembling](https://mlsanity.com/paper/2410.24210/) (2024)
- [Large Language Models Can Automatically Engineer Features for Few-Shot Tabular Learning](https://mlsanity.com/paper/2404.09491/) (2024)
- [Large Scale Transfer Learning for Tabular Data via Language Modeling](https://mlsanity.com/paper/2406.12031/) (2024)
- [Curated LLM: Synergy of LLMs and Data Curation for tabular augmentation in low-data regimes](https://mlsanity.com/paper/2312.12112/) (2023)
- [STUNT: Few-shot Tabular Learning with Self-generated Tasks from Unlabeled Tables](https://mlsanity.com/paper/2303.00918/) (2023)
- [Elephants Never Forget: Memorization and Learning of Tabular Data in Large Language Models](https://mlsanity.com/paper/2404.06209/) (2024)
- [TABLET: Learning From Instructions For Tabular Data](https://mlsanity.com/paper/2304.13188/) (2023)
- [AutoElicit: Using Large Language Models for Expert Prior Elicitation in Predictive Modelling](https://mlsanity.com/paper/2411.17284/) (2024)
- [Trajectories, bifurcations and pseudotime in large clinical datasets: applications to myocardial infarction and diabetes data](https://mlsanity.com/paper/2007.03788/) (2020)
- [LLM Meeting Decision Trees on Tabular Data](https://mlsanity.com/paper/2505.17918/) (2025)
- ["Oh LLM, I'm Asking Thee, Please Give Me a Decision Tree": Zero-Shot Decision Tree Induction and Embedding with Large Language Models](https://mlsanity.com/paper/2409.18594/) (2024)
- [Small Models are LLM Knowledge Triggers on Medical Tabular Prediction](https://mlsanity.com/paper/2403.01570/) (2024)
- [Latte: Transfering LLMs` Latent-level Knowledge for Few-shot Tabular Learning](https://mlsanity.com/paper/2505.05237/) (2025)
- [LLM Empowered Prototype Learning for Zero and Few-Shot Tasks on Tabular Data](https://mlsanity.com/paper/2508.09263/) (2025)

## Abstract (arXiv)

Tabular learning uses structured data to predict target outcomes. Traditionally, this process has relied on labeled data. However, large language models (LLMs) can be used to elicit domain priors based on the task description and feature semantics, thereby enabling predictions without labeled data. We propose Marginal Response Surface Elicitation (MARS), a method that transforms feature-level LLM priors into a reusable, zero-shot tabular classifier. To construct this classifier, MARS selects representative values for each feature from unlabeled data and prompts the LLM to provide corresponding class support scores and feature weights. It then aggregates multiple responses using the median to construct feature response functions, and makes predictions through their weighted sum without further LLM queries. Across eight tabular benchmark tasks, MARS achieves the highest average AUC and AP, outperforming direct prompting by 1.97 and 6.21 percentage points respectively, while substantially reducing end-to-end costs. Evaluations with LLMs of different sizes further demonstrate its predictive advantage over direct prompting.