How large language models need symbolism

While scaling laws grant large language models powerful intuition, the art of the symbol provides the necessary compass for navigating complex frontiers and achieving genuine discovery.

Authors

Xiaotie Deng (ORCID: https://orcid.org/0000-0002-5282-6467)
Hanyu Li (ORCID: https://orcid.org/0000-0002-5013-3333)

Institutions

Peking University (CN)

Publication Details

Journal: National Science Review
Published: 2025-08-18
DOI: https://doi.org/10.1093/nsr/nwaf339
Primary Topic: Topic Modeling
Type: article
Field-Weighted Citation Impact: 0.00

Funders

National Natural Science Foundation of China

Controls

|||

ALL TIME

JAN

FEB

MAR

APR

MAY

JUN

JUL

AUG

SEP

OCT

article

How large language models need symbolism

Xiaotie Deng, Hanyu Li

Aug 18, 2025

National Science Review

Topic Modeling

article

How large language models need symbolism

Xiaotie Deng, Hanyu Li

August 18, 2025article en

Abstract

While scaling laws grant large language models powerful intuition, the art of the symbol provides the necessary compass for navigating complex frontiers and achieving genuine discovery.

National Science ReviewVol. 12(10)

Peking University (CN)

National Natural Science Foundation of China

Openalex Percentile: Top 89%

Topic Modeling

DOI Open Access PDF OpenAlex

AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

How large language models need symbolism — Xiaotie Deng, Hanyu Li · National Science Review (2025) | TGRS Research Map | TGRS