From Prompts to Trees: Effective LLM-Guided Tree Generation for Few-Shot Tabular Classification

cs.LG, cs.AI, cs.CL

Submitted: 2026-10-07

Updated: 2026-10-07

Comments: Accepted to EMNLP 2026 Main as an oral presentation. Code available: https://github.com/yueqiu0/LLMTree

Code: https://github.com/yueqiu0/LLMTree

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Sources

• Qwen Technical Report
• Zero-Shot Decision Tree Construction via Large Language Models
• DeepSeek-V3 Technical Report
• Towards Better Serialization of Tabular Data for Few-shot Classification with Large Language Models
• GPT-4 Technical Report
• Llama 2: Open Foundation and Fine-Tuned Chat Models
• GPTree: Towards Explainable Decision-Making via LLM-powered Decision Trees

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