Cover Image

DSTC: Direct Preference Learning with Only Self-Generated Tests and Code to Improve Code LMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Liu, Zhihan, Zhang, Shenao, Liu, Yongfei, Liu, Boyi, Yang, Yingxiang, Wang, Zhaoran
Format:	Preprint
Published:	2024
Subjects:	Software Engineering Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Klear-CodeTest: Scalable Test Case Generation for Code Reinforcement Learning
by: Fu, Jia, et al.
Published: (2025)

Reward-Augmented Data Enhances Direct Preference Alignment of LLMs
by: Zhang, Shenao, et al.
Published: (2024)

Seed-CTS: Unleashing the Power of Tree Search for Superior Performance in Competitive Coding Tasks
by: Wang, Hao, et al.
Published: (2024)

$\textbf{PLUM}$: Improving Code LMs with Execution-Guided On-Policy Preference Learning Driven By Synthetic Test Cases
by: Zhang, Dylan, et al.
Published: (2024)

Revisit Self-Debugging with Self-Generated Tests for Code Generation
by: Chen, Xiancai, et al.
Published: (2025)

Towards Better Code Understanding in Decoder-Only Models with Contrastive Learning
by: Lin, Jiayi, et al.
Published: (2024)

Afterburner: Reinforcement Learning Facilitates Self-Improving Code Efficiency Optimization
by: Du, Mingzhe, et al.
Published: (2025)

Learning to Align Human Code Preferences
by: Yin, Xin, et al.
Published: (2025)

ACE: Self-Evolving LLM Coding Framework via Adversarial Unit Test Generation and Preference Optimization
by: Huang, Yixu, et al.
Published: (2026)

Improving Code Translation with Syntax-Guided and Semantic-aware Preference Optimization
by: Wu, Yuhan, et al.
Published: (2026)

CodeFort: Robust Training for Code Generation Models
by: Zhang, Yuhao, et al.
Published: (2024)

Beyond Functional Correctness: Exploring Hallucinations in LLM-Generated Code
by: Liu, Fang, et al.
Published: (2024)

BigCodeArena: Unveiling More Reliable Human Preferences in Code Generation via Execution
by: Zhuo, Terry Yue, et al.
Published: (2025)

RedCode: Risky Code Execution and Generation Benchmark for Code Agents
by: Guo, Chengquan, et al.
Published: (2024)

Test-Driven Development for Code Generation
by: Mathews, Noble Saji, et al.
Published: (2024)

XSearch: Explainable Code Search via Concept-to-Code Alignment
by: Liu, Yiming, et al.
Published: (2026)

ContextModule: Improving Code Completion via Repository-level Contextual Information
by: Guan, Zhanming, et al.
Published: (2024)

Nova: Generative Language Models for Assembly Code with Hierarchical Attention and Contrastive Learning
by: Jiang, Nan, et al.
Published: (2023)

Personality-Guided Code Generation Using Large Language Models
by: Guo, Yaoqi, et al.
Published: (2024)

Helping LLMs Improve Code Generation Using Feedback from Testing and Static Analysis
by: Dolcetti, Greta, et al.
Published: (2024)

ReCode: Improving LLM-based Code Repair with Fine-Grained Retrieval-Augmented Generation
by: Zhao, Yicong, et al.
Published: (2025)

Bias Testing and Mitigation in LLM-based Code Generation
by: Huang, Dong, et al.
Published: (2023)

From Context to Intent: Reasoning-Guided Function-Level Code Completion
by: Li, Yanzhou, et al.
Published: (2025)

Adaptive Confidence Gating in Multi-Agent Collaboration for Efficient and Optimized Code Generation
by: Zhang, Haoji, et al.
Published: (2026)

Impact-driven Context Filtering For Cross-file Code Completion
by: Li, Yanzhou, et al.
Published: (2025)

Top Pass: Improve Code Generation by Pass@k-Maximized Code Ranking
by: Lyu, Zhi-Cun, et al.
Published: (2024)

Flow2Code: Evaluating Large Language Models for Flowchart-based Code Generation Capability
by: He, Mengliang, et al.
Published: (2025)

Code Copycat Conundrum: Demystifying Repetition in LLM-based Code Generation
by: Liu, Mingwei, et al.
Published: (2025)

Enhancing LLM-Based Test Generation by Eliminating Covered Code
by: Xu, WeiZhe, et al.
Published: (2026)

SEW: Self-Evolving Agentic Workflows for Automated Code Generation
by: Liu, Siwei, et al.
Published: (2025)

CodeRL+: Improving Code Generation via Reinforcement with Execution Semantics Alignment
by: Jiang, Xue, et al.
Published: (2025)

Multilingual Multimodal Software Developer for Code Generation
by: Chai, Linzheng, et al.
Published: (2025)

CodeDPO: Aligning Code Models with Self Generated and Verified Source Code
by: Zhang, Kechi, et al.
Published: (2024)

Self-Improving Code Generation via Semantic Entropy and Behavioral Consensus
by: Zhang, Huan, et al.
Published: (2026)

TENET: Leveraging Tests Beyond Validation for Code Generation
by: Hu, Yiran, et al.
Published: (2025)

Automated Proof Generation for Rust Code via Self-Evolution
by: Chen, Tianyu, et al.
Published: (2024)

Domain Adaptation for Code Model-based Unit Test Case Generation
by: Shin, Jiho, et al.
Published: (2023)

Detecting Data Poisoning in Code Generation LLMs via Black-Box, Vulnerability-Oriented Scanning
by: Yan, Shenao, et al.
Published: (2026)

Improving LLM Code Generation via Requirement-Aware Curriculum Reinforcement Learning
by: Yin, Shouyu, et al.
Published: (2026)

AutoTest: Evolutionary Code Solution Selection with Test Cases
by: Duan, Zhihua, et al.
Published: (2024)