7 citations · 44 across the 40 of their papers we have counts for
21 papers · 1 filter
Theoretical Proof that Auto-regressive Language Models Collapse when Real-world Data is a Finite Set
Lecheng Wang, Xianjie Shi, Ge Li +5
Auto-regressive language models (LMs) have been widely used to generate data in data-scarce domains to train new LMs, compensating for the scarcity of real-world data. Previous wor…
EvoCodeBench: An Evolving Code Generation Benchmark with Domain-Specific Evaluations
Jia Li, Ge Li, Xuanming Zhang +6
How to evaluate Large Language Models (LLMs) in code generation remains an open question. Existing benchmarks have two limitations - data leakage and lack of domain-specific evalua…
Generating Equivalent Representations of Code By A Self-Reflection Approach
Jia Li, Ge Li, Lecheng Wang +2
Equivalent Representations (ERs) of code are textual representations that preserve the same semantics as the code itself, e.g., natural language comments and pseudocode. ERs play a…
Showing LLM-Generated Code Selectively Based on Confidence of LLMs
Jia Li, Yuqi Zhu, Yongmin Li +2
Large Language Models (LLMs) have shown impressive abilities in code generation, but they may generate erroneous programs. Reading a program takes ten times longer than writing it.…
aiXcoder-7B: A Lightweight and Effective Large Language Model for Code Processing
Siyuan Jiang, Jia Li, He Zong +11
Large Language Models (LLMs) have been widely used in code completion, and researchers are focusing on scaling up LLMs to improve their accuracy. However, larger LLMs have lower in…
CodeDPO: Aligning Code Models with Self Generated and Verified Source Code
Kechi Zhang, Ge Li, Yihong Dong +5
Code generation models have shown significant potential for programming tasks. However, existing training methods like supervised fine-tuning face key limitations: they do not effe…
FAN: Fourier Analysis Networks
Yihong Dong, Ge Li, Yongding Tao +7
Despite the remarkable successes of general-purpose neural networks, such as MLPs and Transformers, we find that they exhibit notable shortcomings in modeling and reasoning about p…
Sifting through the Chaff: On Utilizing Execution Feedback for Ranking the Generated Code Candidates
Zhihong Sun, Yao Wan, Jia Li +4
Large Language Models (LLMs), such as GPT-4, StarCoder, and CodeLlama, are transforming the way developers approach programming by automatically generating code based on given natu…
M2CVD: Enhancing Vulnerability Semantic through Multi-Model Collaboration for Code Vulnerability Detection
Ziliang Wang, Ge Li, Jia Li +3
Large Language Models (LLMs) have strong capabilities in code comprehension, but fine-tuning costs and semantic alignment issues limit their project-specific optimization; converse…
Line-level Semantic Structure Learning for Code Vulnerability Detection
Ziliang Wang, Ge Li, Jia Li +3
Unlike the flow structure of natural languages, programming languages have an inherent rigidity in structure and grammar.However, existing detection methods based on pre-trained mo…
DevEval: A Manually-Annotated Code Generation Benchmark Aligned with Real-World Code Repositories
Jia Li, Ge Li, Yunfei Zhao +15
How to evaluate the coding abilities of Large Language Models (LLMs) remains an open question. We find that existing benchmarks are poorly aligned with real-world code repositories…
Exploring and Unleashing the Power of Large Language Models in Automated Code Translation
Zhen Yang, Fang Liu, Zhongxing Yu +7
Code translation tools (transpilers) are developed for automatic source-to-source translation. Although learning-based transpilers have shown impressive enhancement against rule-ba…
EvoCodeBench: An Evolving Code Generation Benchmark Aligned with Real-World Code Repositories
Jia Li, Ge Li, Xuanming Zhang +2
How to evaluate Large Language Models (LLMs) in code generation is an open question. Existing benchmarks demonstrate poor alignment with real-world code repositories and are insuff…
Enhancing Code Generation Performance of Smaller Models by Distilling the Reasoning Ability of LLMs
Zhihong Sun, Chen Lyu, Bolun Li +4
Large Language Models (LLMs) have recently made significant advances in code generation through the 'Chain-of-Thought' prompting technique. This technique empowers the model to aut…
HiRoPE: Length Extrapolation for Code Models Using Hierarchical Position
Kechi Zhang, Ge Li, Huangzhao Zhang +1
Addressing the limitation of context length in large language models for code-related tasks is the primary focus of this paper. Existing LLMs are constrained by their pre-trained c…
Exploring Data-Efficient Adaptation of Large Language Models for Code Generation
Xue Jiang, Yihong Dong, Zhiyuan Fan +3
Although Large Language Models (LLMs) have made significant progress in code generation, they still struggle with code generation tasks in specific scenarios. These scenarios usual…
IRCoCo: Immediate Rewards-Guided Deep Reinforcement Learning for Code Completion
Bolun Li, Zhihong Sun, Tao Huang +5
Code completion aims to enhance programming productivity by predicting potential code based on the current programming context. Recently, pretrained language models (LMs) have beco…
Generalization or Memorization: Data Contamination and Trustworthy Evaluation for Large Language Models
Yihong Dong, Xue Jiang, Huanyu Liu +4
Recent statements about the impressive capabilities of large language models (LLMs) are usually supported by evaluating on open-access benchmarks. Considering the vast size and wid…
Knowledge-Aware Code Generation with Large Language Models
Tao Huang, Zhihong Sun, Zhi Jin +2
Large Language Models (LLMs) perform well on basic programming problems. However, they encounter challenges when dealing with complex tasks involving the use of diverse algorithmic…
CodeAgent: Enhancing Code Generation with Tool-Integrated Agent Systems for Real-World Repo-level Coding Challenges
Kechi Zhang, Jia Li, Ge Li +2
Large Language Models (LLMs) have shown promise in automated code generation but typically excel only in simpler tasks such as generating standalone code units. Real-world software…
DevEval: Evaluating Code Generation in Practical Software Projects
Jia Li, Ge Li, Yunfei Zhao +14
How to evaluate Large Language Models (LLMs) in code generation is an open question. Many benchmarks have been proposed but are inconsistent with practical software projects, e.g.,…