Saved in:
Bibliographic Details
Main Authors: Zhang, Erica, Goto, Ryunosuke, Sagan, Naomi, Mutter, Jurik, Phillips, Nick, Alizadeh, Ash, Lee, Kangwook, Blanchet, Jose, Pilanci, Mert, Tibshirani, Robert
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2502.10648
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916891973386240
author Zhang, Erica
Goto, Ryunosuke
Sagan, Naomi
Mutter, Jurik
Phillips, Nick
Alizadeh, Ash
Lee, Kangwook
Blanchet, Jose
Pilanci, Mert
Tibshirani, Robert
author_facet Zhang, Erica
Goto, Ryunosuke
Sagan, Naomi
Mutter, Jurik
Phillips, Nick
Alizadeh, Ash
Lee, Kangwook
Blanchet, Jose
Pilanci, Mert
Tibshirani, Robert
contents We introduce LLM-Lasso, a novel framework that leverages large language models (LLMs) to guide feature selection in Lasso $\ell_1$ regression. Unlike traditional methods that rely solely on numerical data, LLM-Lasso incorporates domain-specific knowledge extracted from natural language, enhanced through a retrieval-augmented generation (RAG) pipeline, to seamlessly integrate data-driven modeling with contextual insights. Specifically, the LLM generates penalty factors for each feature, which are converted into weights for the Lasso penalty using a simple, tunable model. Features identified as more relevant by the LLM receive lower penalties, increasing their likelihood of being retained in the final model, while less relevant features are assigned higher penalties, reducing their influence. Importantly, LLM-Lasso has an internal validation step that determines how much to trust the contextual knowledge in our prediction pipeline. Hence it addresses key challenges in robustness, making it suitable for mitigating potential inaccuracies or hallucinations from the LLM. In various biomedical case studies, LLM-Lasso outperforms standard Lasso and existing feature selection baselines, all while ensuring the LLM operates without prior access to the datasets. To our knowledge, this is the first approach to effectively integrate conventional feature selection techniques directly with LLM-based domain-specific reasoning.
format Preprint
id arxiv_https___arxiv_org_abs_2502_10648
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle LLM-Lasso: A Robust Framework for Domain-Informed Feature Selection and Regularization
Zhang, Erica
Goto, Ryunosuke
Sagan, Naomi
Mutter, Jurik
Phillips, Nick
Alizadeh, Ash
Lee, Kangwook
Blanchet, Jose
Pilanci, Mert
Tibshirani, Robert
Machine Learning
We introduce LLM-Lasso, a novel framework that leverages large language models (LLMs) to guide feature selection in Lasso $\ell_1$ regression. Unlike traditional methods that rely solely on numerical data, LLM-Lasso incorporates domain-specific knowledge extracted from natural language, enhanced through a retrieval-augmented generation (RAG) pipeline, to seamlessly integrate data-driven modeling with contextual insights. Specifically, the LLM generates penalty factors for each feature, which are converted into weights for the Lasso penalty using a simple, tunable model. Features identified as more relevant by the LLM receive lower penalties, increasing their likelihood of being retained in the final model, while less relevant features are assigned higher penalties, reducing their influence. Importantly, LLM-Lasso has an internal validation step that determines how much to trust the contextual knowledge in our prediction pipeline. Hence it addresses key challenges in robustness, making it suitable for mitigating potential inaccuracies or hallucinations from the LLM. In various biomedical case studies, LLM-Lasso outperforms standard Lasso and existing feature selection baselines, all while ensuring the LLM operates without prior access to the datasets. To our knowledge, this is the first approach to effectively integrate conventional feature selection techniques directly with LLM-based domain-specific reasoning.
title LLM-Lasso: A Robust Framework for Domain-Informed Feature Selection and Regularization
topic Machine Learning
url https://arxiv.org/abs/2502.10648