Regional Tiny Stories: Using Small Models to Compare Language Learning and Tokenizer Performance
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_ | 1866915253004009472 |
|---|---|
| author | Patil, Nirvan Inamdar, Malhar Abhay Gosai, Agnivo Pathak, Guruprasad Joshi, Anish Sagavekar, Aryan Joshirao, Anish Dandekar, Raj Dandekar, Rajat Panat, Sreedath |
| author_facet | Patil, Nirvan Inamdar, Malhar Abhay Gosai, Agnivo Pathak, Guruprasad Joshi, Anish Sagavekar, Aryan Joshirao, Anish Dandekar, Raj Dandekar, Rajat Panat, Sreedath |
| contents | Small Language Models (SLMs) offer efficient alternatives to LLMs for specific domains. The 2023 TinyStories study developed an English dataset that allows SLMs with 1 to 10 million parameters to produce coherent outputs. Our research expands this framework by translating the original dataset into Indian languages and creating synthetic data using LLMs. We focus on Hindi, Marathi, and Bengali, evaluating SLMs for regional language processing and understanding linguistic complexity. We show that SLMs efficiently process regional languages with significantly fewer parameters than LLMs, providing a complementary framework for ``inference based evaluation" of tokenization strategies and linguistic complexity. Our analysis shows that language-specific tokenizers outperform general-purpose ones for Indian languages. Empirical validations, supported by information-theoretic and morphological analyses, provides fundamental understanding behind the better performance of Hindi models over Marathi and Bengali. Additionally, we show that synthetic datasets outperform translated content for training SLMs. Correlation analyses reveal cross-linguistic patterns and language-specific relationships between creativity, grammatical precision, and narrative completeness. These findings advance both the practical application of SLMs to underserved languages and our theoretical understanding of neural language development. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_07989 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Regional Tiny Stories: Using Small Models to Compare Language Learning and Tokenizer Performance Patil, Nirvan Inamdar, Malhar Abhay Gosai, Agnivo Pathak, Guruprasad Joshi, Anish Sagavekar, Aryan Joshirao, Anish Dandekar, Raj Dandekar, Rajat Panat, Sreedath Computation and Language Artificial Intelligence Small Language Models (SLMs) offer efficient alternatives to LLMs for specific domains. The 2023 TinyStories study developed an English dataset that allows SLMs with 1 to 10 million parameters to produce coherent outputs. Our research expands this framework by translating the original dataset into Indian languages and creating synthetic data using LLMs. We focus on Hindi, Marathi, and Bengali, evaluating SLMs for regional language processing and understanding linguistic complexity. We show that SLMs efficiently process regional languages with significantly fewer parameters than LLMs, providing a complementary framework for ``inference based evaluation" of tokenization strategies and linguistic complexity. Our analysis shows that language-specific tokenizers outperform general-purpose ones for Indian languages. Empirical validations, supported by information-theoretic and morphological analyses, provides fundamental understanding behind the better performance of Hindi models over Marathi and Bengali. Additionally, we show that synthetic datasets outperform translated content for training SLMs. Correlation analyses reveal cross-linguistic patterns and language-specific relationships between creativity, grammatical precision, and narrative completeness. These findings advance both the practical application of SLMs to underserved languages and our theoretical understanding of neural language development. |
| title | Regional Tiny Stories: Using Small Models to Compare Language Learning and Tokenizer Performance |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2504.07989 |