Large Language Models for Limited Noisy Data: A Gravitational Wave Identification Study

TL;DR

This study demonstrates that large language models can effectively identify gravitational wave signals from limited, noisy observational data, outperforming traditional neural networks and scaling predictably with model and data size.

Contribution

The paper shows that LLMs can directly learn from observational data in noisy regimes, reducing reliance on large simulated datasets for gravitational wave detection.

Findings

LLMs achieve 97.4% accuracy with limited data

Additional simulated data does not improve LLM performance

Performance scales predictably with model and dataset size

Abstract

This work investigates whether large language models (LLMs) offer advantages over traditional neural networks for astronomical data processing, in regimes with non-Gaussian, non-stationary noise and limited labeled samples. Gravitational wave observations provide an suitable test case, using only 90 LIGO events, finetuned LLMs achieve 97.4\% accuracy for identifying signals. Further experiments show that, in contrast to traditional networks that rely on large simulated datasets, additional simulated samples do not improve LLM performance, while scaling studies reveal predictable gains with increasing model size and dataset size. These results indicate that LLMs can extract discriminative structure directly from observational data and provide an efficient assessment for gravitational wave identification. The same strategy may extend to other astronomical domains with similar noise properties, such as radio or pulsar observations.