Search Results for author:
Found 14 papers, 3 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.
Studying LLM Performance on Closed- and Open-source Data
We find that performance for C# changes little from OSS --> proprietary code, but does significantly reduce for C++; we find that this difference is attributable to differences in identifiers.
Better patching using LLM prompting, via Self-Consistency
Large Language models (LLMs) can be induced to solve non-trivial problems with "few-shot" prompts including illustrative problem-solution examples.
Automatic Semantic Augmentation of Language Model Prompts (for Code Summarization)
This approach improves performance in several different settings suggested by prior work, including for two different Large Language Models.
Extending Source Code Pre-Trained Language Models to Summarise Decompiled Binaries
While the automated summarisation of decompiled code can help Reverse Engineers understand and analyse binaries, current work mainly focuses on summarising source code, and no suitable dataset exists for this task.
Few-shot training LLMs for project-specific code-summarization
Very large language models (LLMs), such as GPT-3 and Codex have achieved state-of-the-art performance on several natural-language tasks, and show great promise also for code.
NatGen: Generative pre-training by "Naturalizing" source code
Pre-trained Generative Language models (e. g. PLBART, CodeT5, SPT-Code) for source code yielded strong results on several tasks in the past few years, including code generation and translation.
Learning code summarization from a small and local dataset
We compare several models and training approaches, including same-project training, cross-project training, training a model especially designed to be sample efficient (and thus prima facie well-suited for learning in a limited-sample same-project setting) and a maximalist hybrid approach, fine-tuning first on many projects in many languages and then training on the same-project.
Multilingual training for Software Engineering
As a way around such data bottlenecks, we present evidence suggesting that human-written code in different languages (which performs the same function), is rather similar, and particularly preserving of identifier naming patterns; we further present evidence suggesting that identifiers are a very important element of training data for software engineering tasks.
Ranked #5 on
Type prediction
on ManyTypes4TypeScript
SYNFIX: Automatically Fixing Syntax Errors using Compiler Diagnostics
Beginning programmers struggle with the complex grammar of modern programming languages like Java, and make lot of syntax errors.
Learning to Infer Run-Time Invariants from Source code
Source code is notably different from natural language in that it is meant to be executed.
Patching as Translation: the Data and the Metaphor
Given these findings, we demonstrate how a more principled approach to model design, based on our empirical findings and general knowledge of software development, can lead to better solutions.
A Survey of Machine Learning for Big Code and Naturalness
We contrast programming languages against natural languages and discuss how these similarities and differences drive the design of probabilistic models.
OntoCat: Automatically categorizing knowledge in API Documentation
Most application development happens in the context of complex APIs; reference documentation for APIs has grown tremendously in variety, complexity, and volume, and can be difficult to navigate.
