Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2504.09798 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910932232306688 |
|---|---|
| author | Wijaya, Sandya Bolano, Jacob Soteres, Alejandro Gomez Kode, Shriyanshu Huang, Yue Sahai, Anant |
| author_facet | Wijaya, Sandya Bolano, Jacob Soteres, Alejandro Gomez Kode, Shriyanshu Huang, Yue Sahai, Anant |
| contents | Large Language Models (LLMs) often struggle with code generation tasks involving niche software libraries. Existing code generation techniques with only human-oriented documentation can fail -- even when the LLM has access to web search and the library is documented online. To address this challenge, we propose ReadMe$.$LLM, LLM-oriented documentation for software libraries. By attaching the contents of ReadMe$.$LLM to a query, performance consistently improves to near-perfect accuracy, with one case study demonstrating up to 100% success across all tested models. We propose a software development lifecycle where LLM-specific documentation is maintained alongside traditional software updates. In this study, we present two practical applications of the ReadMe$.$LLM idea with diverse software libraries, highlighting that our proposed approach could generalize across programming domains. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_09798 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | ReadMe.LLM: A Framework to Help LLMs Understand Your Library Wijaya, Sandya Bolano, Jacob Soteres, Alejandro Gomez Kode, Shriyanshu Huang, Yue Sahai, Anant Software Engineering Large Language Models (LLMs) often struggle with code generation tasks involving niche software libraries. Existing code generation techniques with only human-oriented documentation can fail -- even when the LLM has access to web search and the library is documented online. To address this challenge, we propose ReadMe$.$LLM, LLM-oriented documentation for software libraries. By attaching the contents of ReadMe$.$LLM to a query, performance consistently improves to near-perfect accuracy, with one case study demonstrating up to 100% success across all tested models. We propose a software development lifecycle where LLM-specific documentation is maintained alongside traditional software updates. In this study, we present two practical applications of the ReadMe$.$LLM idea with diverse software libraries, highlighting that our proposed approach could generalize across programming domains. |
| title | ReadMe.LLM: A Framework to Help LLMs Understand Your Library |
| topic | Software Engineering |
| url | https://arxiv.org/abs/2504.09798 |