AI Paper Atlas

Research map / Probabilistic and scientific modeling / Molecules and proteins

RAG-SR: Retrieval-Augmented Generation for Neural Symbolic Regression

Hengzhe Zhang, Qi Chen, Bing XUE, Wolfgang Banzhaf, Mengjie Zhang

ICLR 2025 · Probabilistic and scientific modeling › Molecules and proteins · approach: Statistical analysis of ML practice

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes RAG-SR, a retrieval-augmented generation approach for neural symbolic regression that retrieves relevant expressions to guide generation, aiming to avoid heavy pre-training and handle unseen functions and variables.

Problem

Symbolic regression: discovering mathematical expressions that best describe a dataset. Existing neural approaches rely on pre-trained models that need large compute and struggle with unseen functions and variables.

Approach

Applies retrieval-augmented generation to symbolic regression so that a generator is guided by retrieved relevant expressions, removing the need for a large pre-trained model (only the abstract is available, so details beyond this are unknown).

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy