Repository-Aware File Path Retrieval via Fine-Tuned LLMs
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_ | 1866911201731018752 |
|---|---|
| author | Yanuganti, Vasudha Puri, Ishaan Chhatre, Swapnil Singh, Mantinder Jallepalli, Ashok Shrivastava, Hritvik Sharma, Pradeep Kumar |
| author_facet | Yanuganti, Vasudha Puri, Ishaan Chhatre, Swapnil Singh, Mantinder Jallepalli, Ashok Shrivastava, Hritvik Sharma, Pradeep Kumar |
| contents | Modern codebases make it hard for developers and AI coding assistants to find the right source files when answering questions like "How does this feature work?" or "Where was the bug introduced?" Traditional code search (keyword or IR based) often misses semantic context and cross file links, while large language models (LLMs) understand natural language but lack repository specific detail. We present a method for file path retrieval that fine tunes a strong LLM (Qwen3-8B) with QLoRA and Unsloth optimizations to predict relevant file paths directly from a natural language query. To build training data, we introduce six code aware strategies that use abstract syntax tree (AST) structure and repository content to generate realistic question-answer pairs, where answers are sets of file paths. The strategies range from single file prompts to hierarchical repository summaries, providing broad coverage. We fine tune on Python projects including Flask, Click, Jinja, FastAPI, and PyTorch, and obtain high retrieval accuracy: up to 91\% exact match and 93\% recall on held out queries, clearly beating single strategy training. On a large codebase like PyTorch (about 4,000 Python files), the model reaches 59\% recall, showing scalability. We analyze how multi level code signals help the LLM reason over cross file context and discuss dataset design, limits (for example, context length in very large repos), and future integration of retrieval with LLM based code intelligence. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_08850 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Repository-Aware File Path Retrieval via Fine-Tuned LLMs Yanuganti, Vasudha Puri, Ishaan Chhatre, Swapnil Singh, Mantinder Jallepalli, Ashok Shrivastava, Hritvik Sharma, Pradeep Kumar Software Engineering Artificial Intelligence Modern codebases make it hard for developers and AI coding assistants to find the right source files when answering questions like "How does this feature work?" or "Where was the bug introduced?" Traditional code search (keyword or IR based) often misses semantic context and cross file links, while large language models (LLMs) understand natural language but lack repository specific detail. We present a method for file path retrieval that fine tunes a strong LLM (Qwen3-8B) with QLoRA and Unsloth optimizations to predict relevant file paths directly from a natural language query. To build training data, we introduce six code aware strategies that use abstract syntax tree (AST) structure and repository content to generate realistic question-answer pairs, where answers are sets of file paths. The strategies range from single file prompts to hierarchical repository summaries, providing broad coverage. We fine tune on Python projects including Flask, Click, Jinja, FastAPI, and PyTorch, and obtain high retrieval accuracy: up to 91\% exact match and 93\% recall on held out queries, clearly beating single strategy training. On a large codebase like PyTorch (about 4,000 Python files), the model reaches 59\% recall, showing scalability. We analyze how multi level code signals help the LLM reason over cross file context and discuss dataset design, limits (for example, context length in very large repos), and future integration of retrieval with LLM based code intelligence. |
| title | Repository-Aware File Path Retrieval via Fine-Tuned LLMs |
| topic | Software Engineering Artificial Intelligence |
| url | https://arxiv.org/abs/2510.08850 |