Search Results for author:
Found 12 papers, 6 papers with code
Trojans in Large Language Models of Code: A Critical Review through a Trigger-Based Taxonomy
Large language models (LLMs) have provided a lot of exciting new capabilities in software development.
On Trojan Signatures in Large Language Models of Code
Trojan signatures, as described by Fields et al. (2021), are noticeable differences in the distribution of the trojaned class parameters (weights) and the non-trojaned class parameters of the trojaned model, that can be used to detect the trojaned model.
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.
A Study of Variable-Role-based Feature Enrichment in Neural Models of Code
In this paper, we explore the impact of an unsuperivsed feature enrichment approach based on variable roles on the performance of neural models of code.
Study of Distractors in Neural Models of Code
Understanding distractors provide a complementary view of the features' relevance in the predictions of neural models.
Syntax-Guided Program Reduction for Understanding Neural Code Intelligence Models
Our experiments on multiple models across different types of input programs show that the syntax-guided program reduction technique is faster and provides smaller sets of key tokens in reduced programs.
Extracting Label-specific Key Input Features for Neural Code Intelligence Models
The code intelligence (CI) models are often black-box and do not offer any insights on the input features that they learn for making correct predictions.
Code2Snapshot: Using Code Snapshots for Learning Representations of Source Code
We evaluate several variations of this representation and compare its performance with state-of-the-art representations that utilize the rich syntactic and semantic features of input programs.
Memorization and Generalization in Neural Code Intelligence Models
The goal of this paper is to evaluate and compare the extent of memorization and generalization in neural code intelligence models.
Understanding Neural Code Intelligence Through Program Simplification
Our approach, SIVAND, uses simplification techniques that reduce the size of input programs of a CI model while preserving the predictions of the model.
On the Generalizability of Neural Program Models with respect to Semantic-Preserving Program Transformations
With the prevalence of publicly available source code repositories to train deep neural network models, neural program models can do well in source code analysis tasks such as predicting method names in given programs that cannot be easily done by traditional program analysis techniques.
Evaluation of Generalizability of Neural Program Analyzers under Semantic-Preserving Transformations
The abundance of publicly available source code repositories, in conjunction with the advances in neural networks, has enabled data-driven approaches to program analysis.
