Optimizing Small Language Models for NL2SQL via Chain-of-Thought Fine-Tuning
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917359464218624 |
|---|---|
| author | Solanki, Anshul Latawa, Sanchit Chakraborty, Koushik Kamboj, Navneet |
| author_facet | Solanki, Anshul Latawa, Sanchit Chakraborty, Koushik Kamboj, Navneet |
| contents | Translating Natural Language to SQL (NL2SQL) remains a critical bottleneck for democratization of data in enterprises. Although Large Language Models (LLMs) like Gemini 2.5 and other LLMs have demonstrated impressive zero-shot capabilities, their high inference costs limit deployment at scale. This paper explores the efficacy of fine-tuning both large and small language models on NL2SQL tasks.
Our research reveals a counter-intuitive scaling phenomenon. Fine-tuning large models (Gemini 2.5 Flash/Lite) on standard datasets yields negligible returns, often leading to overfitting on complex queries. Conversely, small models (Qwen) show significant gains. Fine-tuning improved the small model baseline from 36% to 45%, and further enriching the dataset with explicit Chain-of-Thought (CoT) reasoning surged accuracy to 54.5%(Fig 2). While this is still lower than the accuracy of large models like Gemini 2.5 , it does serve the business goal of significant cost reduction, latency in inference time and also meeting the business critical performance accuracy threshold.This paper demonstrates that transferring reasoning patterns enables compute-efficient smaller models to approach production-grade performance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_22942 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Optimizing Small Language Models for NL2SQL via Chain-of-Thought Fine-Tuning Solanki, Anshul Latawa, Sanchit Chakraborty, Koushik Kamboj, Navneet Artificial Intelligence Translating Natural Language to SQL (NL2SQL) remains a critical bottleneck for democratization of data in enterprises. Although Large Language Models (LLMs) like Gemini 2.5 and other LLMs have demonstrated impressive zero-shot capabilities, their high inference costs limit deployment at scale. This paper explores the efficacy of fine-tuning both large and small language models on NL2SQL tasks. Our research reveals a counter-intuitive scaling phenomenon. Fine-tuning large models (Gemini 2.5 Flash/Lite) on standard datasets yields negligible returns, often leading to overfitting on complex queries. Conversely, small models (Qwen) show significant gains. Fine-tuning improved the small model baseline from 36% to 45%, and further enriching the dataset with explicit Chain-of-Thought (CoT) reasoning surged accuracy to 54.5%(Fig 2). While this is still lower than the accuracy of large models like Gemini 2.5 , it does serve the business goal of significant cost reduction, latency in inference time and also meeting the business critical performance accuracy threshold.This paper demonstrates that transferring reasoning patterns enables compute-efficient smaller models to approach production-grade performance. |
| title | Optimizing Small Language Models for NL2SQL via Chain-of-Thought Fine-Tuning |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2603.22942 |