Repository-Aware File Path Retrieval via Fine-Tuned LLMs

• URL: http://arxiv.org/abs/2510.08850v1
• Date: Thu, 09 Oct 2025 22:49:10 GMT
• Title: Repository-Aware File Path Retrieval via Fine-Tuned LLMs
• Abstract summary: Large language models (LLMs) understand natural language but lack repository specific detail.<n>We present a method for file path retrieval that fine tunes a strong LLM with QLoRA and Unsloth optimizations.<n>We fine tune on Python projects including Flask, Click, Jinja, FastAPI, and PyTorch, and obtain high retrieval accuracy.
• Score: 0.11726720776908518
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• RepoReasoner: Evaluating Repository-Level Code Reasoning Ability of Long-Context Language Models [54.53236295237077]
  We introduce RepoReasoner, a benchmark for evaluating repository-level code reasoning.<n> Output Prediction measures fine-grained, stateful execution reasoning across files.<n>Call Chain Prediction evaluates high-level architectural dependency understanding under noisy context.
  arXiv  Detail & Related papers  (2026-07-28T17:12:41Z)
• Prompting-MammAlps: Fine-Grained Text-to-Video Retrieval for Camera-Trap Data [49.717366362764956]
  Text-to-Video retrieval (TVR) methods based on large video-language models (VLMs) have potential to retrieve events of interest by describing them with simple text queries.<n>In this work, we introduce Prompting-MammAlps, the first camera-trap TV benchmark, and propose a fine-grained and interpretable TVR method.<n>Specifically, we trained a vision transformer to performtemporal action localization, and convert its output to structured text, describing each video.<n>Independently, ethology-inspired queries are processed by a Large-Language Model (LLM) based agent
  arXiv  Detail & Related papers  (2026-07-10T18:09:41Z)
• ReContext: Recursive Evidence Replay as LLM Harness for Long-Context Reasoning [78.94047086588078]
  We propose Recursive Evidence as LLM Harness for Long-Context Reasoning.<n>It is a training-free inference method for improving long-context reasoning.<n> Experiments on eight long-context datasets with 128K context length show it consistently improves evidence utilization.
  arXiv  Detail & Related papers  (2026-07-02T17:59:26Z)
• Beyond Code Snippets: Benchmarking LLMs on Repository-Level Question Answering [4.120344028676837]
  Large Language Models (LLMs) have shown impressive capabilities across software engineering tasks, including question answering (QA)<n>We introduce StackRepoQA, the first multi-project, repository-level question answering dataset constructed from 1,318 real developer questions and accepted answers across 134 open-source Java projects.
  arXiv  Detail & Related papers  (2026-03-27T16:30:54Z)
• Prompting is not Enough: Exploring Knowledge Integration and Controllable Generation [89.65955788873532]
  Open-domain question answering (OpenQA) represents a cornerstone in natural language processing (NLP)<n>We propose a novel framework named GenKI, which aims to improve the OpenQA performance by exploring Knowledge Integration and controllable Generation.
  arXiv  Detail & Related papers  (2025-05-26T08:18:33Z)
• Emulating Retrieval Augmented Generation via Prompt Engineering for Enhanced Long Context Comprehension in LLMs [23.960451986662996]
  This paper proposes a method that emulates Retrieval Augmented Generation (RAG) through specialized prompt engineering and chain-of-thought reasoning.<n>We evaluate our approach on selected tasks from BABILong, which interleaves standard bAbI QA problems with large amounts of distractor text.
  arXiv  Detail & Related papers  (2025-02-18T02:49:40Z)
• Repository-level Code Search with Neural Retrieval Methods [25.222964965449286]
  We define the task of repository-level code search as retrieving the set of files from the current state of a code repository that are most relevant to addressing a user's question or bug.<n>The proposed approach combines BM25-based retrieval over commit messages with neural reranking using CodeBERT to identify the most pertinent files.<n> Experiments on a new dataset created from 7 popular open-source repositories demonstrate substantial improvements of up to 80% in MAP, MRR and P@1 over the BM25 baseline.
  arXiv  Detail & Related papers  (2025-02-10T21:59:01Z)
• Grounding by Trying: LLMs with Reinforcement Learning-Enhanced Retrieval [55.63711219190506]
  Large language models (LLMs) often struggle with posing the right search queries. We introduce $underlineLe$arning to $underlineRe$trieve by $underlineT$rying (LeReT) LeReT can improve the absolute retrieval accuracy by up to 29% and the downstream generator evaluations by 17%.
  arXiv  Detail & Related papers  (2024-10-30T17:02:54Z)
• PyBench: Evaluating LLM Agent on various real-world coding tasks [13.347173063163138]
  PyBench is a benchmark covering five main categories of real-world tasks, covering more than 10 types of files. Our evaluations indicate that current open-source LLMs are struggling with these tasks. Our fine-tuned 8B size model: textbfPyLlama3 achieves an exciting performance on PyBench.
  arXiv  Detail & Related papers  (2024-07-23T15:23:14Z)
• Hierarchical Context Pruning: Optimizing Real-World Code Completion with Repository-Level Pretrained Code LLMs [24.00351065427465]
  We propose a strategy named Hierarchical Context Pruning (HCP) to construct completion prompts with high informational code content. The HCP models the code repository at the function level, maintaining the topological dependencies between code files while removing a large amount of irrelevant code content.
  arXiv  Detail & Related papers  (2024-06-26T12:26:16Z)
• Call Me When Necessary: LLMs can Efficiently and Faithfully Reason over Structured Environments [40.95811668230818]
  We propose Reasoning-Path-Editing (Readi) to efficiently reason over structured environments. Readi generates a reasoning path given a query, and edit the path only when necessary. Experimental results on three KGQA and two TableQA datasets show the effectiveness of Readi.
  arXiv  Detail & Related papers  (2024-03-13T14:59:07Z)
• DIVKNOWQA: Assessing the Reasoning Ability of LLMs via Open-Domain Question Answering over Knowledge Base and Text [73.68051228972024]
  Large Language Models (LLMs) have exhibited impressive generation capabilities, but they suffer from hallucinations when relying on their internal knowledge. Retrieval-augmented LLMs have emerged as a potential solution to ground LLMs in external knowledge.
  arXiv  Detail & Related papers  (2023-10-31T04:37:57Z)
• An In-Context Schema Understanding Method for Knowledge Base Question Answering [70.87993081445127]
  Large Language Models (LLMs) have shown strong capabilities in language understanding and can be used to solve this task. Existing methods bypass this challenge by initially employing LLMs to generate drafts of logic forms without schema-specific details. We propose a simple In-Context Understanding (ICSU) method that enables LLMs to directly understand schemas by leveraging in-context learning.
  arXiv  Detail & Related papers  (2023-10-22T04:19:17Z)
• Allies: Prompting Large Language Model with Beam Search [107.38790111856761]
  In this work, we propose a novel method called ALLIES. Given an input query, ALLIES leverages LLMs to iteratively generate new queries related to the original query. By iteratively refining and expanding the scope of the original query, ALLIES captures and utilizes hidden knowledge that may not be directly through retrieval.
  arXiv  Detail & Related papers  (2023-05-24T06:16:44Z)
• Large Language Models are Strong Zero-Shot Retriever [89.16756291653371]
  We propose a simple method that applies a large language model (LLM) to large-scale retrieval in zero-shot scenarios. Our method, the Language language model as Retriever (LameR), is built upon no other neural models but an LLM.
  arXiv  Detail & Related papers  (2023-04-27T14:45:55Z)
• CoCoMIC: Code Completion By Jointly Modeling In-file and Cross-file Context [82.88371379927112]
  We propose a framework that incorporates cross-file context to learn the in-file and cross-file context jointly on top of pretrained code LMs. CoCoMIC successfully improves the existing code LM with a 33.94% relative increase in exact match and a 28.69% relative increase in identifier matching for code completion when the cross-file context is provided.
  arXiv  Detail & Related papers  (2022-12-20T05:48:09Z)
• Self-Prompting Large Language Models for Zero-Shot Open-Domain QA [67.08732962244301]
  Open-Domain Question Answering (ODQA) aims to answer questions without explicitly providing background documents. This task becomes notably challenging in a zero-shot setting where no data is available to train tailored retrieval-reader models. We propose a Self-Prompting framework to explicitly utilize the massive knowledge encoded in the parameters of Large Language Models.
  arXiv  Detail & Related papers  (2022-12-16T18:23:43Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.