Leveraging Statistical Machine Translation for Code Search
H Phan, A Jannesari - Proceedings of the 28th International Conference …, 2024 - dl.acm.org
… code compared to expected code, including metrics like CodeBLEU [31] and ParaBLEU [44].
With advancements in … In a manner similar to pseudocode-to-code training using Machine …
With advancements in … In a manner similar to pseudocode-to-code training using Machine …
ITERTL: An Iterative Framework for Fine-tuning LLMs for RTL Code Generation
… 2019. Spoc: search-based pseudocode to code. Advances in Neural Information Processing
Systems, 32. [7] Hung Le, Yue Wang, Akhilesh Deepak Gotmare, Silvio Savarese, and …
Systems, 32. [7] Hung Le, Yue Wang, Akhilesh Deepak Gotmare, Silvio Savarese, and …
Boldly Going Where No Benchmark Has Gone Before: Exposing Bias and Shortcomings in Code Generation Evaluation
… in the popularity of large language models (LLMs) has also been accompanied by
significant advancements in code-generation LLMs (Code-LLMs). Prominent examples of such …
significant advancements in code-generation LLMs (Code-LLMs). Prominent examples of such …
The Larger the Better? Improved LLM Code-Generation via Budget Reallocation
… We begin by describing pass@k (Kulal et al., 2019), the current main approach for … , Oded
Padon, Alex Aiken, and Percy S Liang. Spoc: Search-based pseudocode to code. In H. Wallach…
Padon, Alex Aiken, and Percy S Liang. Spoc: Search-based pseudocode to code. In H. Wallach…
Reuse, Don't Retrain: A Recipe for Continued Pretraining of Language Models
… While these advancements have enabled language models (LMs) to become highlyskilled …
2019). Lastly, our source code data is drawn from permissively licensed GitHub repositories …
2019). Lastly, our source code data is drawn from permissively licensed GitHub repositories …
Re (gEx| DoS) Eval: Evaluating Generated Regular Expressions and their Proneness to DoS Attacks
… With the recent advances of code generation techniques based on Large Language
Models (LLMs), developers are … Advances in neural information processing systems 31 (2018). …
Models (LLMs), developers are … Advances in neural information processing systems 31 (2018). …
Beyond Code: Evaluate Thought Steps for Complex Code Generation
… Code generation aims to generate code in a general-purpose programming language, such
… -guided code generation,” a task that assesses the quality of both thought steps and code …
… -guided code generation,” a task that assesses the quality of both thought steps and code …
RoCode: A Dataset for Measuring Code Intelligence from Problem Definitions in Romanian
… a difficult task, even for the most advanced LLMs. Currently, there are no datasets to … 2019),
but they are geared towards code generation from some text input (docstrings or pseudocode…
but they are geared towards code generation from some text input (docstrings or pseudocode…
Towards ai-assisted synthesis of verified dafny methods
… program veri cation are now within reach of codegenerating large language models. Likewise,
program veri cation systems can … performance using the pass@k metric [Kulal et al. 2019; …
program veri cation systems can … performance using the pass@k metric [Kulal et al. 2019; …
FuncEvalGMN: Evaluating Functional Correctness of SQL via Graph Matching Network
Y Zhan, Y Sun, H Weng, L Cui, G Wang, J Xie… - arXiv preprint arXiv …, 2024 - arxiv.org
In this paper, we propose a novel graph-based methodology to evaluate the functional
correctness of SQL generation. Conventional metrics for assessing SQL code generation, such as …
correctness of SQL generation. Conventional metrics for assessing SQL code generation, such as …