Citation-Grounded Code Comprehension: Preventing LLM Hallucination Through Hybrid Retrieval and Graph-Augmented Context

TL;DR

This paper proposes a hybrid retrieval approach combining textual, semantic, and structural analysis to improve citation accuracy and prevent hallucinations in LLM-based code comprehension tools, validated on Python repositories.

Contribution

It introduces a hybrid retrieval system with graph expansion that significantly enhances citation accuracy and evidence discovery in code comprehension, addressing hallucination issues.

Findings

Achieved 92% citation accuracy with zero hallucinations.

Hybrid retrieval outperforms single modality baselines by 14-18%.

Discovered cross file evidence in 62% of architectural queries.

Abstract

Large language models have become essential tools for code comprehension, enabling developers to query unfamiliar codebases through natural language interfaces. However, LLM hallucination, generating plausible but factually incorrect citations to source code, remains a critical barrier to reliable developer assistance. This paper addresses the challenges of achieving verifiable, citation grounded code comprehension through hybrid retrieval and lightweight structural reasoning. Our work is grounded in systematic evaluation across 30 Python repositories with 180 developer queries, comparing retrieval modalities, graph expansion strategies, and citation verification mechanisms. We find that challenges of citation accuracy arise from the interplay between sparse lexical matching, dense semantic similarity, and cross file architectural dependencies. Among these, cross file evidence discovery is the largest contributor to citation completeness, but it is largely overlooked because existing systems rely on pure textual similarity without leveraging code structure. We advocate for citation grounded generation as an architectural principle for code comprehension systems and demonstrate this need by achieving 92 percent citation accuracy with zero hallucinations. Specifically, we develop a hybrid retrieval system combining BM25 sparse matching, BGE dense embeddings, and Neo4j graph expansion via import relationships, which outperforms single mode baselines by 14 to 18 percentage points while discovering cross file evidence missed by pure text similarity in 62 percent of architectural queries.