no code implementations • 25 May 2023 • Abhinav Jain, Chima Adiole, Swarat Chaudhuri, Thomas Reps, Chris Jermaine
Our experiments show that RLCF raises the odds that an LLM-generated program compiles, is executable, and produces the right output on tests, often allowing LLMs to match the performance of 2x-8x larger LLMs.
1 code implementation • 3 Mar 2021 • Jordan Henkel, Denini Silva, Leopoldo Teixeira, Marcelo d'Amorim, Thomas Reps
Furthermore, in a "time-travel" analysis of broken Dockerfiles that were later fixed, we found that SHIPWRIGHT proposed repairs that were equivalent to human-authored patches in 22. 77% of the cases we studied.
Language Modelling Software Engineering
no code implementations • 29 Apr 2020 • Zi Wang, Ben Liblit, Thomas Reps
TOFU is also input-structure aware (i. e., the search makes use of a specification of a superset of the program's allowed inputs).
Software Engineering
1 code implementation • 7 Feb 2020 • Goutham Ramakrishnan, Jordan Henkel, Zi Wang, Aws Albarghouthi, Somesh Jha, Thomas Reps
Deep neural networks are vulnerable to adversarial examples - small input perturbations that result in incorrect predictions.
no code implementations • 27 Apr 2019 • Jordan Henkel, Shuvendu K. Lahiri, Ben Liblit, Thomas Reps
Using this dataset, we show that interesting clusters can be recovered, in a fully automatic way, by leveraging unsupervised learning in the form of word embeddings.
1 code implementation • 18 Mar 2018 • Jordan Henkel, Shuvendu K. Lahiri, Ben Liblit, Thomas Reps
With the rise of machine learning, there is a great deal of interest in treating programs as data to be fed to learning algorithms.
Software Engineering