Salvato in:
| Autori principali: | , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2509.17866 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914290581110784 |
|---|---|
| author | He, Xinyu Cao, Xianghui |
| author_facet | He, Xinyu Cao, Xianghui |
| contents | Post-training fundamentally alters the behavior of large language models (LLMs), yet its impact on the internal parameter space remains poorly understood. In this work, we conduct a systematic singular value decomposition (SVD) analysis of principal linear layers in pretrained LLMs, focusing on two widely adopted post-training methods: instruction tuning and long-chain-of-thought (Long-CoT) distillation. Our analysis reveals two unexpected and robust structural changes: (1) a near-uniform geometric scaling of singular values across layers; and (2) highly consistent orthogonal transformations are applied to the left and right singular vectors of each matrix. Based on these findings, We propose a simple yet effective framework to describe the coordinated dynamics of parameters in LLMs, which elucidates why post-training inherently relies on the foundational capabilities developed during pre-training. Further experiments demonstrate that singular value scaling underpins the temperature-controlled regulatory mechanisms of post-training, while the coordinated rotation of singular vectors encodes the essential semantic alignment. These results challenge the prevailing view of the parameter space in large models as a black box, uncovering the first clear regularities in how parameters evolve during training, and providing a new perspective for deeper investigation into model parameter changes. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_17866 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Understanding Post-Training Structural Changes in Large Language Models He, Xinyu Cao, Xianghui Machine Learning Artificial Intelligence Post-training fundamentally alters the behavior of large language models (LLMs), yet its impact on the internal parameter space remains poorly understood. In this work, we conduct a systematic singular value decomposition (SVD) analysis of principal linear layers in pretrained LLMs, focusing on two widely adopted post-training methods: instruction tuning and long-chain-of-thought (Long-CoT) distillation. Our analysis reveals two unexpected and robust structural changes: (1) a near-uniform geometric scaling of singular values across layers; and (2) highly consistent orthogonal transformations are applied to the left and right singular vectors of each matrix. Based on these findings, We propose a simple yet effective framework to describe the coordinated dynamics of parameters in LLMs, which elucidates why post-training inherently relies on the foundational capabilities developed during pre-training. Further experiments demonstrate that singular value scaling underpins the temperature-controlled regulatory mechanisms of post-training, while the coordinated rotation of singular vectors encodes the essential semantic alignment. These results challenge the prevailing view of the parameter space in large models as a black box, uncovering the first clear regularities in how parameters evolve during training, and providing a new perspective for deeper investigation into model parameter changes. |
| title | Understanding Post-Training Structural Changes in Large Language Models |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2509.17866 |