RLDBF: Enhancing LLMs Via Reinforcement Learning With DataBase FeedBack

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Dai, Weichen, Dai, Zijie, Huang, Zhijie, Pan, Yixuan, Li, Xinhe, Li, Xi, Zhou, Yi, Qi, Ji, Jiang, Wu
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909566665490432
author Dai, Weichen
Dai, Zijie
Huang, Zhijie
Pan, Yixuan
Li, Xinhe
Li, Xi
Zhou, Yi
Qi, Ji
Jiang, Wu
author_facet Dai, Weichen
Dai, Zijie
Huang, Zhijie
Pan, Yixuan
Li, Xinhe
Li, Xi
Zhou, Yi
Qi, Ji
Jiang, Wu
contents While current large language models (LLMs) demonstrate remarkable linguistic capabilities through training on massive unstructured text corpora, they remain inadequate in leveraging structured scientific data (e.g., chemical molecular properties in databases) that encapsulate centuries of accumulated scientific expertise. These structured datasets hold strategic significance for advancing AI for Science yet current approaches merely treat them as auxiliary supplements to unstructured text. This study pioneers a systematic investigation into enhancing LLMs with structured scientific data, using chemical molecular science as a testbed. We investigate the impact of incorporating molecular property data on LLM across distinct training phases, including continual pre-training, supervised fine-tuning, and reinforcement learning. Notably, to address the inherent limitation of numerical insensitivity in large models, we propose an innovative methodology termed "Reinforcement Learning with Database Feedback" (RLDBF). Experimental evaluations demonstrate the efficacy of the proposed approach, with the model exhibiting remarkable generalization capabilities on previously unseen data and other chemical tasks. The results substantiate the potential of our method in advancing the field of structured scientific data processing within LLMs.
format Preprint
id arxiv_https___arxiv_org_abs_2504_03713
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle RLDBF: Enhancing LLMs Via Reinforcement Learning With DataBase FeedBack
Dai, Weichen
Dai, Zijie
Huang, Zhijie
Pan, Yixuan
Li, Xinhe
Li, Xi
Zhou, Yi
Qi, Ji
Jiang, Wu
Machine Learning
Artificial Intelligence
Computational Engineering, Finance, and Science
While current large language models (LLMs) demonstrate remarkable linguistic capabilities through training on massive unstructured text corpora, they remain inadequate in leveraging structured scientific data (e.g., chemical molecular properties in databases) that encapsulate centuries of accumulated scientific expertise. These structured datasets hold strategic significance for advancing AI for Science yet current approaches merely treat them as auxiliary supplements to unstructured text. This study pioneers a systematic investigation into enhancing LLMs with structured scientific data, using chemical molecular science as a testbed. We investigate the impact of incorporating molecular property data on LLM across distinct training phases, including continual pre-training, supervised fine-tuning, and reinforcement learning. Notably, to address the inherent limitation of numerical insensitivity in large models, we propose an innovative methodology termed "Reinforcement Learning with Database Feedback" (RLDBF). Experimental evaluations demonstrate the efficacy of the proposed approach, with the model exhibiting remarkable generalization capabilities on previously unseen data and other chemical tasks. The results substantiate the potential of our method in advancing the field of structured scientific data processing within LLMs.
title RLDBF: Enhancing LLMs Via Reinforcement Learning With DataBase FeedBack
topic Machine Learning
Artificial Intelligence
Computational Engineering, Finance, and Science
url https://arxiv.org/abs/2504.03713