Salvato in:
Dettagli Bibliografici
Autori principali: Romaszewski, Michał, Sekuła, Przemysław, Głomb, Przemysław, Cholewa, Michał, Kołodziej, Katarzyna
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:https://arxiv.org/abs/2406.04926
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916279586127872
author Romaszewski, Michał
Sekuła, Przemysław
Głomb, Przemysław
Cholewa, Michał
Kołodziej, Katarzyna
author_facet Romaszewski, Michał
Sekuła, Przemysław
Głomb, Przemysław
Cholewa, Michał
Kołodziej, Katarzyna
contents Large Language Models (LLMs) have shown exceptional performance in text processing. Notably, LLMs can synthesize information from large datasets and explain their decisions similarly to human reasoning through a chain of thought (CoT). An emerging application of LLMs is the handling and interpreting of numerical data, where fine-tuning enhances their performance over basic inference methods. This paper proposes a novel approach to training LLMs using knowledge transfer from a random forest (RF) ensemble, leveraging its efficiency and accuracy. By converting RF decision paths into natural language statements, we generate outputs for LLM fine-tuning, enhancing the model's ability to classify and explain its decisions. Our method includes verifying these rules through established classification metrics, ensuring their correctness. We also examine the impact of preprocessing techniques on the representation of numerical data and their influence on classification accuracy and rule correctness
format Preprint
id arxiv_https___arxiv_org_abs_2406_04926
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Through the Thicket: A Study of Number-Oriented LLMs derived from Random Forest Models
Romaszewski, Michał
Sekuła, Przemysław
Głomb, Przemysław
Cholewa, Michał
Kołodziej, Katarzyna
Computation and Language
Machine Learning
Large Language Models (LLMs) have shown exceptional performance in text processing. Notably, LLMs can synthesize information from large datasets and explain their decisions similarly to human reasoning through a chain of thought (CoT). An emerging application of LLMs is the handling and interpreting of numerical data, where fine-tuning enhances their performance over basic inference methods. This paper proposes a novel approach to training LLMs using knowledge transfer from a random forest (RF) ensemble, leveraging its efficiency and accuracy. By converting RF decision paths into natural language statements, we generate outputs for LLM fine-tuning, enhancing the model's ability to classify and explain its decisions. Our method includes verifying these rules through established classification metrics, ensuring their correctness. We also examine the impact of preprocessing techniques on the representation of numerical data and their influence on classification accuracy and rule correctness
title Through the Thicket: A Study of Number-Oriented LLMs derived from Random Forest Models
topic Computation and Language
Machine Learning
url https://arxiv.org/abs/2406.04926