Stale repository context in code RAG actively induces models to produce obsolete helper references, raising stale outputs by 76-88 percentage points over current-only retrieval in a 17-sample diagnostic study.
Arks: Active retrieval in knowledge soup for code generation
7 Pith papers cite this work, alongside 1 external citations. Polarity classification is still indexing.
7
Pith papers citing it
1
external citations · external index
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
SrDetection detects data leakage in Code LLMs via contrast between original benchmark samples and their semantic variants, reporting F1 gains of 21.52 (gray-box) and 14.46 (black-box) over baselines in a controlled testbed.
Internal attention in LLMs shows a bell-curve relevance distribution across layers, enabling Selective-ICR that cuts inference latency 30-50% and lets an 8B zero-shot model match 14B RL re-rankers on BRIGHT.
An LLM-based agent with dual-tier static/dynamic checking and an HLS knowledge graph reaches 0.9826 coverage and 0.9533 consistency on 107 benchmark pairs, beating AST, RAG, and iterative baselines.
A survey classifying RAG foundations for AIGC, summarizing enhancements, cross-modal applications, benchmarks, limitations, and future directions.
Tokalator is a toolkit with VS Code extension, calculators, and community resources to monitor and optimize token usage in AI coding environments.
A systematic literature review that organizes recent work on LLMs for code generation into a taxonomy covering data curation, model advances, evaluations, ethics, environmental impact, and applications, with benchmark comparisons.
citing papers explorer
-
When Retrieval Hurts Code Completion: A Diagnostic Study of Stale Repository Context
Stale repository context in code RAG actively induces models to produce obsolete helper references, raising stale outputs by 76-88 percentage points over current-only retrieval in a 17-sample diagnostic study.
-
SrDetection: A Self-Referential Framework for Data Leakage Detection in Code Large Language Models
SrDetection detects data leakage in Code LLMs via contrast between original benchmark samples and their semantic variants, reporting F1 gains of 21.52 (gray-box) and 14.46 (black-box) over baselines in a controlled testbed.
-
Where Relevance Emerges: A Layer-Wise Study of Internal Attention for Zero-Shot Re-Ranking
Internal attention in LLMs shows a bell-curve relevance distribution across layers, enabling Selective-ICR that cuts inference latency 30-50% and lets an 8B zero-shot model match 14B RL re-rankers on BRIGHT.
-
Shift-Left High-Level Synthesis Verification via Knowledge-Augmented LLM Agent
An LLM-based agent with dual-tier static/dynamic checking and an HLS knowledge graph reaches 0.9826 coverage and 0.9533 consistency on 107 benchmark pairs, beating AST, RAG, and iterative baselines.
-
Retrieval-Augmented Generation for AI-Generated Content: A Survey
A survey classifying RAG foundations for AIGC, summarizing enhancements, cross-modal applications, benchmarks, limitations, and future directions.
-
Tokalator: A Context Engineering Toolkit for Artificial Intelligence Coding Assistants
Tokalator is a toolkit with VS Code extension, calculators, and community resources to monitor and optimize token usage in AI coding environments.
-
A Survey on Large Language Models for Code Generation
A systematic literature review that organizes recent work on LLMs for code generation into a taxonomy covering data curation, model advances, evaluations, ethics, environmental impact, and applications, with benchmark comparisons.