# A Lightweight Framework for Adaptive Retrieval In Code Completion With Critique Model

arXiv: https://arxiv.org/abs/2406.10263 · HTML: https://mlsanity.com/paper/2406.10263/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in RAG for code, one of 15 directions in Retrieval-augmented generation.
- Builds on 22 of its 42 references that are in the map.
- First posted on arXiv 11 Jun 2024.

## Placed in

- Retrieval-augmented generation / [RAG for code](https://mlsanity.com/rag/rag-for-code/)

## Builds on (most cited first, 22 of 22)

- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift](https://mlsanity.com/paper/1906.02530/) (2019)
- [DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence](https://mlsanity.com/paper/2401.14196/) (2024)
- [CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis](https://mlsanity.com/paper/2203.13474/) (2022)
- [A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challenges](https://mlsanity.com/paper/2011.06225/) (2020)
- [Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation](https://mlsanity.com/paper/2302.09664/) (2023)
- [The Internal State of an LLM Knows When It's Lying](https://mlsanity.com/paper/2304.13734/) (2023)
- [UniXcoder: Unified Cross-Modal Pre-training for Code Representation](https://mlsanity.com/paper/2203.03850/) (2022)
- [Enhancing Retrieval-Augmented Large Language Models with Iterative Retrieval-Generation Synergy](https://mlsanity.com/paper/2305.15294/) (2023)
- [INSIDE: LLMs' Internal States Retain the Power of Hallucination Detection](https://mlsanity.com/paper/2402.03744/) (2024)
- [IntelliCode Compose: Code Generation Using Transformer](https://mlsanity.com/paper/2005.08025/) (2020)
- [Unsupervised Quality Estimation for Neural Machine Translation](https://mlsanity.com/paper/2005.10608/) (2020)
- [Practical Program Repair in the Era of Large Pre-trained Language Models](https://mlsanity.com/paper/2210.14179/) (2022)
- [Unsupervised Real-Time Hallucination Detection based on the Internal States of Large Language Models](https://mlsanity.com/paper/2403.06448/) (2024)
- [Uncertainty Estimation and Quantification for LLMs: A Simple Supervised Approach](https://mlsanity.com/paper/2404.15993/) (2024)
- [When Do LLMs Need Retrieval Augmentation? Mitigating LLMs' Overconfidence Helps Retrieval Augmentation](https://mlsanity.com/paper/2402.11457/) (2024)
- [Repoformer: Selective Retrieval for Repository-Level Code Completion](https://mlsanity.com/paper/2403.10059/) (2024)
- [Dataflow-Guided Retrieval Augmentation for Repository-Level Code Completion](https://mlsanity.com/paper/2405.19782/) (2024)
- [REPOFUSE: Repository-Level Code Completion with Fused Dual Context](https://mlsanity.com/paper/2402.14323/) (2024)
- [Prompt-based Code Completion via Multi-Retrieval Augmented Generation](https://mlsanity.com/paper/2405.07530/) (2024)
- [Long-Range Modeling of Source Code Files with eWASH: Extended Window Access by Syntax Hierarchy](https://mlsanity.com/paper/2109.08780/) (2021)

## Abstract (arXiv)

Recent advancements in Retrieval-Augmented Generation have significantly enhanced code completion at the repository level. Various RAG-based code completion systems are proposed based on different design choices. For instance, gaining more effectiveness at the cost of repeating the retrieval-generation process multiple times. However, the indiscriminate use of retrieval in current methods reveals issues in both efficiency and effectiveness, as a considerable portion of retrievals are unnecessary and may introduce unhelpful or even harmful suggestions to code language models. To address these challenges, we introduce CARD, a lightweight critique method designed to provide insights into the necessity of retrievals and select the optimal answer from multiple predictions. CARD can seamlessly integrate into any RAG-based code completion system. Our evaluation shows that CARD saves 21% to 46% times of retrieval for Line completion, 14% to 40% times of retrieval for API completion, and 6% to 46.5% times of retrieval for function completion respectively, while improving the accuracy. CARD reduces latency ranging from 16% to 83%. CARD is generalizable to different LMs, retrievers, and programming languages. It is lightweight with training in few seconds and inference in few milliseconds.