Long Text to Predictive Features: LLM-Guided Blockwise Feature Engineering via Executable Program Search
cs.LG, cs.CL
Submitted: 2026-10-08
Updated: 2026-10-08
Code: https://github.com/ByteDance-Seed/seed-oss
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- LLM-FE: Automated Feature Engineering for Tabular Data with LLMs as Evolutionary Optimizers
- LLMs as Feature Engineers for Text-and-Tabular Prediction
- Longformer: The Long-Document Transformer
- FAMOSE: A ReAct Approach to Automated Feature Discovery
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- Tabular Feature Discovery With Reasoning Type Exploration
- AlphaEvolve: A coding agent for scientific and algorithmic discovery
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks