Uncovering Scaling Laws for Large Language Models via Inverse Problems
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909779334529024 |
|---|---|
| author | Verma, Arun Wu, Zhaoxuan Zhou, Zijian Lin, Xiaoqiang Chen, Zhiliang Sim, Rachael Hwee Ling Qiao, Rui Wang, Jingtan Bui, Nhung Niu, Xinyuan Hu, Wenyang Lau, Gregory Kang Ruey Khoo, Zi-Yu Zhao, Zitong Xu, Xinyi Hemachandra, Apivich Ng, See-Kiong Low, Bryan Kian Hsiang |
| author_facet | Verma, Arun Wu, Zhaoxuan Zhou, Zijian Lin, Xiaoqiang Chen, Zhiliang Sim, Rachael Hwee Ling Qiao, Rui Wang, Jingtan Bui, Nhung Niu, Xinyuan Hu, Wenyang Lau, Gregory Kang Ruey Khoo, Zi-Yu Zhao, Zitong Xu, Xinyi Hemachandra, Apivich Ng, See-Kiong Low, Bryan Kian Hsiang |
| contents | Large Language Models (LLMs) are large-scale pretrained models that have achieved remarkable success across diverse domains. These successes have been driven by unprecedented complexity and scale in both data and computations. However, due to the high costs of training such models, brute-force trial-and-error approaches to improve LLMs are not feasible. Inspired by the success of inverse problems in uncovering fundamental scientific laws, this position paper advocates that inverse problems can also efficiently uncover scaling laws that guide the building of LLMs to achieve the desirable performance with significantly better cost-effectiveness. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_07909 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Uncovering Scaling Laws for Large Language Models via Inverse Problems Verma, Arun Wu, Zhaoxuan Zhou, Zijian Lin, Xiaoqiang Chen, Zhiliang Sim, Rachael Hwee Ling Qiao, Rui Wang, Jingtan Bui, Nhung Niu, Xinyuan Hu, Wenyang Lau, Gregory Kang Ruey Khoo, Zi-Yu Zhao, Zitong Xu, Xinyi Hemachandra, Apivich Ng, See-Kiong Low, Bryan Kian Hsiang Machine Learning Artificial Intelligence Computation and Language Large Language Models (LLMs) are large-scale pretrained models that have achieved remarkable success across diverse domains. These successes have been driven by unprecedented complexity and scale in both data and computations. However, due to the high costs of training such models, brute-force trial-and-error approaches to improve LLMs are not feasible. Inspired by the success of inverse problems in uncovering fundamental scientific laws, this position paper advocates that inverse problems can also efficiently uncover scaling laws that guide the building of LLMs to achieve the desirable performance with significantly better cost-effectiveness. |
| title | Uncovering Scaling Laws for Large Language Models via Inverse Problems |
| topic | Machine Learning Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2509.07909 |