Search Results for author:
Found 6 papers, 4 papers with code
Resolving Crash Bugs via Large Language Models: An Empirical Study
Evaluating IntDiagSolver on multiple LLMs reveals consistent enhancement in the accuracy of crash bug resolution, including ChatGPT, Claude, and CodeLlama.
CodeGen4Libs: A Two-Stage Approach for Library-Oriented Code Generation
To evaluate the effectiveness of our approach, we conduct extensive experiments on a dataset of 403, 780 data items.
ClassEval: A Manually-Crafted Benchmark for Evaluating LLMs on Class-level Code Generation
Third, we find that generating the entire class all at once (i. e. holistic generation strategy) is the best generation strategy only for GPT-4 and GPT-3. 5, while method-by-method generation (i. e. incremental and compositional) is better strategies for the other models with limited ability of understanding long instructions and utilizing the middle information.
Evaluating Instruction-Tuned Large Language Models on Code Comprehension and Generation
First, for the zero-shot setting, instructed LLMs are very competitive on code comprehension and generation tasks and sometimes even better than small SOTA models specifically fine-tuned on each downstream task.
KNOD: Domain Knowledge Distilled Tree Decoder for Automated Program Repair
KNOD has two major novelties, including (1) a novel three-stage tree decoder, which directly generates Abstract Syntax Trees of patched code according to the inherent tree structure, and (2) a novel domain-rule distillation, which leverages syntactic and semantic rules and teacher-student distributions to explicitly inject the domain knowledge into the decoding procedure during both the training and inference phases.
An Empirical Study on Deployment Faults of Deep Learning Based Mobile Applications
In contrast, faults related to the deployment of DL models on mobile devices (named as deployment faults of mobile DL apps) have not been well studied.
