Pith. sign in

REVIEW 4 cited by

Large Language Models Can Automatically Engineer Features for Few-Shot Tabular Learning

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2404.09491 v2 pith:3LJA53CZ submitted 2024-04-15 cs.LG

classification cs.LG
keywords learningfeatllmtabularfeaturesllmsfew-shotframeworkinference
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Large Language Models (LLMs), with their remarkable ability to tackle challenging and unseen reasoning problems, hold immense potential for tabular learning, that is vital for many real-world applications. In this paper, we propose a novel in-context learning framework, FeatLLM, which employs LLMs as feature engineers to produce an input data set that is optimally suited for tabular predictions. The generated features are used to infer class likelihood with a simple downstream machine learning model, such as linear regression and yields high performance few-shot learning. The proposed FeatLLM framework only uses this simple predictive model with the discovered features at inference time. Compared to existing LLM-based approaches, FeatLLM eliminates the need to send queries to the LLM for each sample at inference time. Moreover, it merely requires API-level access to LLMs, and overcomes prompt size limitations. As demonstrated across numerous tabular datasets from a wide range of domains, FeatLLM generates high-quality rules, significantly (10% on average) outperforming alternatives such as TabLLM and STUNT.

Discussion (0). Sign in to comment.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Parameter-Free Encoders Remain Viable for RDB Foundation Models

    cs.LG 2026-07 conditional novelty 6.0 of 10

    Trainable RDB encoders cannot robustly exploit neighborhood labels as fixed foundation-model features or feature-importance signals, so simple parameter-free encoders stay near-SOTA.

  2. MedFeat: Model-Aware and Explainability-Driven Feature Engineering with LLMs for Clinical Tabular Prediction

    cs.LG 2026-02 conditional novelty 6.0 of 10

    MedFeat iteratively prompts an LLM to create clinical features guided by SHAP importance and the downstream model's inductive bias, improving tabular prediction AUC/F1 on five EHR tasks.

  3. AUTOCT: Automating Interpretable Clinical Trial Prediction with LLM Agents

    cs.LG 2025-06 reject novelty 6.0 of 10

    AutoCT achieves test ROC-AUC 0.753, 0.639, and 0.702 on Phase I/II/III trial approval prediction using 100-sample subsets and LLM-generated features.

  4. LLM-ML Teaming: Integrated Symbolic Decoding and Gradient Search for Valid and Stable Generative Feature Transformation

    cs.LG 2025-06 conditional novelty 4.0 of 10

    A product-of-experts decoder that blends a fine-tuned LLM's token probabilities with a gradient-searched sequence decoder produces more valid and stable feature transformations than either alone.

Pith tools