REVIEW 7 cited by
REPOFUSE: Repository-Level Code Completion with Fused Dual Context
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
The success of language models in code assistance has spurred the proposal of repository-level code completion as a means to enhance prediction accuracy, utilizing the context from the entire codebase. However, this amplified context can inadvertently increase inference latency, potentially undermining the developer experience and deterring tool adoption - a challenge we termed the Context-Latency Conundrum. This paper introduces REPOFUSE, a pioneering solution designed to enhance repository-level code completion without the latency trade-off. REPOFUSE uniquely fuses two types of context: the analogy context, rooted in code analogies, and the rationale context, which encompasses in-depth semantic relationships. We propose a novel rank truncated generation (RTG) technique that efficiently condenses these contexts into prompts with restricted size. This enables REPOFUSE to deliver precise code completions while maintaining inference efficiency. Through testing with the CrossCodeEval suite, REPOFUSE has demonstrated a significant leap over existing models, achieving a 40.90% to 59.75% increase in exact match (EM) accuracy for code completions and a 26.8% enhancement in inference speed. Beyond experimental validation, REPOFUSE has been integrated into the workflow of a large enterprise, where it actively supports various coding tasks.
Forward citations
Cited by 7 Pith papers
-
RepoReasoner: Evaluating Repository-Level Code Reasoning Ability of Long-Context Language Models
RepoReasoner is a repository-level code-reasoning benchmark with output-prediction and call-chain tasks; the best LLM reaches only 69.1% Pass@1 even with oracle context, with low recall in dependency tracing.
-
Better Call Grep: Evaluating and Improving Grep-Like Lexical Retrieval for Repository-Level Code Completion
LLM-generated ripgrep queries plus BM25 re-ranking and line-interval de-duplication outperform graph- and RL-based retrievers for repository-level code completion on CrossCodeEval and RepoEval-Updated.
-
Enhancing Project-Specific Code Completion by Inferring Internal API Information
A retrieval-augmented code completion method that infers project-internal APIs from a rough draft and a static knowledge base, beating existing repo-level baselines.
-
Code Graph Model (CGM): A Graph-Integrated Large Language Model for Repository-Level Software Engineering Tasks
A graph-integrated open-source LLM with agentless RAG resolves 43% of SWE-bench Lite issues, best among open-weight models.
-
Beyond "What to Retrieve": Uncertainty in Retrieval-Augmented Code Generation
Uncertainty-aware multi-source retrieval improves GPT repository-level code selection over plain RAG but matches verification-and-repair alone and is backend- and context-dependent.
-
GRACE: Graph-Guided Repository-Aware Code Completion through Hierarchical Code Fusion
GRACE combines a multi-level code graph, hybrid text-structure retrieval, and graph fusion to improve repository-level code completion over vanilla and graph-based RAG baselines.
-
A Deep Dive into Retrieval-Augmented Generation for Code Completion: Experience on WeChat
On WeChat's closed-source codebase, similarity-based RAG with combined BM25 and GTE-Qwen retrieval improves open-source LLM code completion more than identifier-based retrieval, with gains growing for larger models.
Discussion (0). Continue with ORCID to comment.