7 citations · 10 across the 19 of their papers we have counts for
21 papers
Efficient Grammar-Constrained Decoding via Parser Stack Classification
Yongmin Li, Yihong Dong, Jia Li +1
LLMs are widely used to generate structured output like source code or JSON. Grammar-constrained decoding (GCD) can guarantee the syntactic validity of the generated output, by mas…
Evaluating the Formal Reasoning Capabilities of Large Language Models through Chomsky Hierarchy
Yihong Dong, Jianha Xiao, Xue Jiang +7
The formal reasoning capabilities of LLMs are crucial for advancing automated software engineering. However, existing benchmarks for LLMs lack systematic evaluation based on comput…
Learning from Execution: Self-Evolving Memory for Private-Library Code Generation
Mofei Li, Taozhi Chen, Guowei Yang +1
Large Language Models (LLMs) have achieved strong performance on general code generation, but their effectiveness drops sharply in enterprise settings where software development re…
RealBench: A Repo-Level Code Generation Benchmark Aligned with Real-World Software Development Practices
Jia Li, Hongyi Deng, Yiran Zhang +9
Writing code requires significant time and effort in software development. To automate this process, researchers have made substantial progress using Large Language Models (LLMs) f…
KOCO-BENCH: Can Large Language Models Leverage Domain Knowledge in Software Development?
Xue Jiang, Ge Li, Jiaru Qian +12
Large language models (LLMs) excel at general programming but struggle with domain-specific software development, necessitating domain specialization methods for LLMs to learn and…
VulInstruct: Teaching LLMs Root-Cause Reasoning for Vulnerability Detection via Security Specifications
Hao Zhu, Jia Li, Cuiyun Gao +7
Large language models (LLMs) have achieved remarkable progress in code understanding tasks. However, they demonstrate limited performance in vulnerability detection and struggle to…
VulAgent: Hypothesis-Validation based Multi-Agent Vulnerability Detection
Ziliang Wang, Ge Li, Jia Li +2
The application of language models to project-level vulnerability detection remains challenging, owing to the dual requirement of accurately localizing security-sensitive code and…
StackTrans: From Large Language Model to Large Pushdown Automata Model
Kechi Zhang, Ge Li, Jia Li +4
The Transformer architecture has emerged as a landmark advancement within the broad field of artificial intelligence, effectively catalyzing the advent of large language models (LL…
EvoCoT: Overcoming the Exploration Bottleneck in Reinforcement Learning
Huanyu Liu, Jia Li, Yihong Dong +6
Reinforcement learning with verifiable reward (RLVR) has become a promising paradigm for post-training large language models (LLMs) to improve their reasoning capability. However,…
Computational Thinking Reasoning in Large Language Models
Kechi Zhang, Ge Li, Jia Li +8
While large language models (LLMs) have demonstrated remarkable reasoning capabilities, they often struggle with complex tasks that require specific thinking paradigms, such as div…
DAVSP: Safety Alignment for Large Vision-Language Models via Deep Aligned Visual Safety Prompt
Yitong Zhang, Jia Li, Liyi Cai +1
Large Vision-Language Models (LVLMs) have achieved impressive progress across various applications but remain vulnerable to malicious queries that exploit the visual modality. Exis…
SATURN: SAT-based Reinforcement Learning to Unleash LLMs Reasoning
Huanyu Liu, Ge Li, Jia Li +3
How to design reinforcement learning (RL) tasks that effectively unleash the reasoning capability of large language models (LLMs) remains an open question. Existing RL tasks (e.g.,…
Uncertainty-Guided Chain-of-Thought for Code Generation with LLMs
Yuqi Zhu, Ge Li, Xue Jiang +4
Chain-of-Thought (CoT) reasoning has been demonstrated as an effective technique for improving the problem-solving capabilities of large language models (LLMs) in the context of co…
aiXcoder-7B-v2: Training LLMs to Fully Utilize the Long Context in Repository-level Code Completion
Jia Li, Hao Zhu, Huanyu Liu +7
Large Language Models (LLMs) have shown promising results in repository-level code completion, which completes code based on the in-file and cross-file context of a repository. The…
Reasoning is Periodicity? Improving Large Language Models Through Effective Periodicity Modeling
Yihong Dong, Ge Li, Xue Jiang +8
Periodicity, as one of the most important basic characteristics, lays the foundation for facilitating structured knowledge acquisition and systematic cognitive processes within hum…
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…
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…
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…
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…
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…