Zobrazeno 1 - 10
of 122
pro vyhledávání: '"Barr, Earl"'
Autor:
Parasaram, Nikhil, Yan, Huijie, Yang, Boyu, Flahy, Zineb, Qudsi, Abriele, Ziaber, Damian, Barr, Earl, Mechtaev, Sergey
Recent research has shown that incorporating bug-related facts, such as stack traces and GitHub issues, into prompts enhances the bug-fixing capabilities of large language models (LLMs). Considering the ever-increasing context window of these models,
Externí odkaz:
http://arxiv.org/abs/2404.05520
Autor:
Steenhoek, Benjamin, Rahman, Md Mahbubur, Roy, Monoshi Kumar, Alam, Mirza Sanjida, Barr, Earl T., Le, Wei
Large Language Models (LLMs) have demonstrated great potential for code generation and other software engineering tasks. Vulnerability detection is of crucial importance to maintaining the security, integrity, and trustworthiness of software systems.
Externí odkaz:
http://arxiv.org/abs/2403.17218
Autor:
Allamanis, Miltiadis, Barr, Earl T.
Most machine learning models predict a probability distribution over concrete outputs and struggle to accurately predict names over high entropy sequence distributions. Here, we explore finding abstract, high-precision patterns intrinsic to these pre
Externí odkaz:
http://arxiv.org/abs/2308.08203
Autor:
Souza, Leandro O., Barr, Earl T., Petke, Justyna, Almeida, Eduardo S., Neto, Paulo Anselmo M. S.
For companies producing related products, a Software Product Line (SPL) is a software reuse method that improves time-to-market and software quality, achieving substantial cost reductions.These benefits do not come for free. It often takes years to r
Externí odkaz:
http://arxiv.org/abs/2307.10896
Large Language Models (LLM) are a new class of computation engines, "programmed" via prompt engineering. We are still learning how to best "program" these LLMs to help developers. We start with the intuition that developers tend to consciously and un
Externí odkaz:
http://arxiv.org/abs/2304.06815
Background. From information theory, surprisal is a measurement of how unexpected an event is. Statistical language models provide a probabilistic approximation of natural languages, and because surprisal is constructed with the probability of an eve
Externí odkaz:
http://arxiv.org/abs/2204.07363
Type inference over partial contexts in dynamically typed languages is challenging. In this work, we present a graph neural network model that predicts types by probabilistically reasoning over a program's structure, names, and patterns. The network
Externí odkaz:
http://arxiv.org/abs/2004.10657
We present a new approach to the type inference problem for dynamic languages. Our goal is to combine \emph{logical} constraints, that is, deterministic information from a type system, with \emph{natural} constraints, that is, uncertain statistical i
Externí odkaz:
http://arxiv.org/abs/2004.00348
Recently, there has been growing debate as to whether or not static analysis can be truly sound. In spite of this concern, research on techniques seeking to at least partially answer undecidable questions has a long history. However, little attention
Externí odkaz:
http://arxiv.org/abs/1905.12734
We introduce an exploratory study on Mutation Validation (MV), a model validation method using mutated training labels for supervised learning. MV mutates training data labels, retrains the model against the mutated data, then uses the metamorphic re
Externí odkaz:
http://arxiv.org/abs/1905.10201