Search Results for author:
Found 14 papers, 7 papers with code
RepairAgent: An Autonomous, LLM-Based Agent for Program Repair
Unlike existing deep learning-based approaches, which prompt a model with a fixed prompt or in a fixed feedback loop, our work treats the LLM as an agent capable of autonomously planning and executing actions to fix bugs by invoking suitable tools.
Calibration and Correctness of Language Models for Code
Our contributions will lead to better-calibrated decision-making in the current use of code generated by language models, and offers a framework for future research to further improve calibration methods for generative models in Software Engineering.
Fuzz4All: Universal Fuzzing with Large Language Models
Moreover, the inputs generated by existing fuzzers are often limited to specific features of the input language, and thus can hardly reveal bugs related to other or new features.
LExecutor: Learning-Guided Execution
The key idea is to let a neural model predict missing values that otherwise would cause the program to get stuck, and to inject these values into the execution.
Code Generation Tools (Almost) for Free? A Study of Few-Shot, Pre-Trained Language Models on Code
For example, we find that providing a small natural language description of the code generation task is an easy way to improve predictions.
Meta Learning for Code Summarization
Source code summarization is the task of generating a high-level natural language description for a segment of programming language code.
Learning to Make Compiler Optimizations More Effective
Applying the transformations that our model deems most favorable prior to compilation yields an average speedup of 1. 14x.
Neural Software Analysis
The resulting tools complement and outperform traditional program analyses, and are used in industrial practice.
TypeWriter: Neural Type Prediction with Search-based Validation
Unfortunately, static type inference for dynamic languages is inherently limited, while probabilistic approaches suffer from imprecision.
Software Engineering
IdBench: Evaluating Semantic Representations of Identifier Names in Source Code
Our results show that the effectiveness of semantic representations varies significantly and that the best available embeddings successfully represent semantic relatedness.
Neural Bug Finding: A Study of Opportunities and Challenges
Static analysis is one of the most widely adopted techniques to find software bugs before code is put in production.
Small World with High Risks: A Study of Security Threats in the npm Ecosystem
Studying the potential for running vulnerable or malicious code due to third-party dependencies, we find that individual packages could impact large parts of the entire ecosystem.
Cryptography and Security
Context2Name: A Deep Learning-Based Approach to Infer Natural Variable Names from Usage Contexts
Most of the JavaScript code deployed in the wild has been minified, a process in which identifier names are replaced with short, arbitrary and meaningless names.
DeepBugs: A Learning Approach to Name-based Bug Detection
We formulate bug detection as a binary classification problem and train a classifier that distinguishes correct from incorrect code.
Software Engineering Programming Languages
