Cover Image

Bridging Developer Instructions and Code Completion Through Instruction-Aware Fill-in-the-Middle Paradigm

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Sun, Zhensu, Yang, Chengran, Peng, Chao, Gao, Pengfei, Du, Xiaoning, Li, Li, Lo, David
Format:	Preprint
Published:	2025
Subjects:	Software Engineering
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Token Sugar: Making Source Code Sweeter for LLMs through Token-Efficient Shorthand
by: Sun, Zhensu, et al.
Published: (2025)

Don't Complete It! Preventing Unhelpful Code Completion for Productive and Sustainable Neural Code Completion Systems
by: Sun, Zhensu, et al.
Published: (2022)

Think Like Human Developers: Harnessing Community Knowledge for Structured Code Reasoning
by: Yang, Chengran, et al.
Published: (2025)

AI Coders Are Among Us: Rethinking Programming Language Grammar Towards Efficient Code Generation
by: Sun, Zhensu, et al.
Published: (2024)

When Neural Code Completion Models Size up the Situation: Attaining Cheaper and Faster Completion through Dynamic Model Inference
by: Sun, Zhensu, et al.
Published: (2024)

FDI: Attack Neural Code Generation Systems through User Feedback Channel
by: Sun, Zhensu, et al.
Published: (2024)

The Hidden Cost of Readability: How Code Formatting Silently Consumes Your LLM Budget
by: Pan, Dangfeng, et al.
Published: (2025)

Executing as You Generate: Hiding Execution Latency in LLM Code Generation
by: Sun, Zhensu, et al.
Published: (2026)

Towards Agentic Runtime Healing
by: Sun, Zhensu, et al.
Published: (2024)

Autoregressive, Yet Revisable: In Decoding Revision for Secure Code Generation
by: Yang, Chengran, et al.
Published: (2026)

Robustness, Security, Privacy, Explainability, Efficiency, and Usability of Large Language Models for Code
by: Yang, Zhou, et al.
Published: (2024)

ACECode: A Reinforcement Learning Framework for Aligning Code Efficiency and Correctness in Code Language Models
by: Yang, Chengran, et al.
Published: (2024)

From Output to Evaluation: Does Raw Instruction-Tuned Code LLMs Output Suffice for Fill-in-the-Middle Code Generation?
by: Ahmad, Wasi Uddin, et al.
Published: (2025)

Structure-Aware Fill-in-the-Middle Pretraining for Code
by: Gong, Linyuan, et al.
Published: (2025)

Rethinking the Value of Agent-Generated Tests for LLM-Based Software Engineering Agents
by: Chen, Zhi, et al.
Published: (2026)

A Closer Look into Transformer-Based Code Intelligence Through Code Transformation: Challenges and Opportunities
by: Li, Yaoxian, et al.
Published: (2022)

From Completion to Editing: Unlocking Context-Aware Code Infilling via Search-and-Replace Instruction Tuning
by: Zhang, Jiajun, et al.
Published: (2026)

Compiling Code LLMs into Lightweight Executables
by: Shi, Jieke, et al.
Published: (2026)

From Code to Courtroom: LLMs as the New Software Judges
by: He, Junda, et al.
Published: (2025)

CodeOCR: On the Effectiveness of Vision Language Models in Code Understanding
by: Shi, Yuling, et al.
Published: (2026)

LIDL: LLM Integration Defect Localization via Knowledge Graph-Enhanced Multi-Agent Analysis
by: Tan, Gou, et al.
Published: (2026)

TestDecision: Sequential Test Suite Generation via Greedy Optimization and Reinforcement Learning
by: Wang, Guoqing, et al.
Published: (2026)

More with Less: An Empirical Study of Turn-Control Strategies for Efficient Coding Agents
by: Gao, Pengfei, et al.
Published: (2025)

Secure-Instruct: An Automated Pipeline for Synthesizing Instruction-Tuning Datasets Using LLMs for Secure Code Generation
by: Li, Junjie, et al.
Published: (2025)

Evaluation of LLMs on Syntax-Aware Code Fill-in-the-Middle Tasks
by: Gong, Linyuan, et al.
Published: (2024)

Hotfixing Large Language Models for Code
by: Yang, Zhou, et al.
Published: (2024)

Enhancing Project-Specific Code Completion by Inferring Internal API Information
by: Deng, Le, et al.
Published: (2025)

RepoMasterEval: Evaluating Code Completion via Real-World Repositories
by: Wu, Qinyun, et al.
Published: (2024)

Revisiting Code Search in a Two-Stage Paradigm
by: Hu, Fan, et al.
Published: (2022)

APIDocBooster: An Extract-Then-Abstract Framework Leveraging Large Language Models for Augmenting API Documentation
by: Yang, Chengran, et al.
Published: (2023)

ClarEval: A Benchmark for Evaluating Clarification Skills of Code Agents under Ambiguous Instructions
by: Li, Jialin, et al.
Published: (2026)

PseudoBridge: Pseudo Code as the Bridge for Better Semantic and Logic Alignment in Code Retrieval
by: Li, Yixuan, et al.
Published: (2025)

Natural Is The Best: Model-Agnostic Code Simplification for Pre-trained Large Language Models
by: Wang, Yan, et al.
Published: (2024)

A Hierarchical and Evolvable Benchmark for Fine-Grained Code Instruction Following with Multi-Turn Feedback
by: Duan, Guoliang, et al.
Published: (2025)

TIT: A Tree-Structured Instruction Tuning Approach for LLM-Based Code Translation
by: Jiang, He, et al.
Published: (2025)

Identifying and Mitigating API Misuse in Large Language Models
by: Zhuo, Terry Yue, et al.
Published: (2025)

BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions
by: Zhuo, Terry Yue, et al.
Published: (2024)

CREME: Robustness Enhancement of Code LLMs via Layer-Aware Model Editing
by: Liu, Shuhan, et al.
Published: (2025)

CodeIF: Benchmarking the Instruction-Following Capabilities of Large Language Models for Code Generation
by: Yan, Kaiwen, et al.
Published: (2025)

Bridging Design and Development with Automated Declarative UI Code Generation
by: Zhou, Ting, et al.
Published: (2024)