Gespeichert in:
| Hauptverfasser: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2512.04031 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866911367756251136 |
|---|---|
| author | Li, Yixuan Lu, Yuhao Liu, Yang Li, Liang Ruffini, R. Li, Di Cai, Rong-Gen Zhu, Xiaoyan Lin, Wenbin Wang, Yu |
| author_facet | Li, Yixuan Lu, Yuhao Liu, Yang Li, Liang Ruffini, R. Li, Di Cai, Rong-Gen Zhu, Xiaoyan Lin, Wenbin Wang, Yu |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_04031 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Large Language Models for Limited Noisy Data: A Gravitational Wave Identification Study Li, Yixuan Lu, Yuhao Liu, Yang Li, Liang Ruffini, R. Li, Di Cai, Rong-Gen Zhu, Xiaoyan Lin, Wenbin Wang, Yu Instrumentation and Methods for Astrophysics High Energy Astrophysical Phenomena Artificial Intelligence 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. |
| title | Large Language Models for Limited Noisy Data: A Gravitational Wave Identification Study |
| topic | Instrumentation and Methods for Astrophysics High Energy Astrophysical Phenomena Artificial Intelligence |
| url | https://arxiv.org/abs/2512.04031 |