Related papers: Trace Refinement in B and Event-B

Pretrained large language models (LLMs) are able to solve a wide variety of tasks through transfer learning. Various explainability methods have been developed to investigate their decision making process. TracIn (Pruthi et al., 2020) is…

Correct operation of many critical systems is dependent on the data consistency and integrity properties of underlying databases. Therefore, a verifiable and rigorous database design process is highly desirable. This research aims to…

Recent trends in the machine learning community show that models with fidelity toward human perceptual measurements perform strongly on vision tasks. Likewise, human behavioral measurements have been used to regularize model performance.…

Software is now ubiquitous and involved in complex interactions with the human users and the physical world in so-called cyber-physical systems where the management of time is a major issue. Separation of concerns is a key asset in the…

We explore advanced fine-tuning techniques to boost BERT's performance in sentiment analysis, paraphrase detection, and semantic textual similarity. Our approach leverages SMART regularization to combat overfitting, improves hyperparameter…

Event-B is a refinement-based formal method that has been shown to be useful in developing concurrent and distributed programs. Large models can be decomposed into sub-models that can be refined semi-independently and executed in parallel.…

Models such as finite state automata are widely used to abstract the behavior of software systems by capturing the sequences of events observable during their execution. Nevertheless, models rarely exist in practice and, when they do, get…

In this paper we present a variant of message sequence diagrams called EETs Extended Event Traces We provide the graphical notation discuss the methodological use of EETs to describe behavior of object oriented business information systems…

Representation learning is a critical ingredient for natural language processing systems. Recent Transformer language models like BERT learn powerful textual representations, but these models are targeted towards token- and sentence-level…

Tracking entities in procedural language requires understanding the transformations arising from actions on entities as well as those entities' interactions. While self-attention-based pre-trained language encoders like GPT and BERT have…

We study the problem of incorporating prior knowledge into a deep Transformer-based model,i.e.,Bidirectional Encoder Representations from Transformers (BERT), to enhance its performance on semantic textual matching tasks. By probing and…

While pretrained models such as BERT have shown large gains across natural language understanding tasks, their performance can be improved by further training the model on a data-rich intermediate task, before fine-tuning it on a target…

Refinement transforms an abstract system model into a concrete, executable program, such that properties established for the abstract model carry over to the concrete implementation. Refinement has been used successfully in the development…

It is challenging to control the quality of online information due to the lack of supervision over all the information posted online. Manual checking is almost impossible given the vast number of posts made on online media and how quickly…

Particle tracking is crucial for almost all physics analysis programs at the Large Hadron Collider. Deep learning models are pervasively used in particle tracking related tasks. However, the current practice is to design and train one deep…

Language models like BERT excel at sentence classification tasks due to extensive pre-training on general data, but their robustness to parameter corruption is unexplored. To understand this better, we look at what happens if a language…

TREB, a novel tabular imputation framework utilizing BERT, introduces a groundbreaking approach for handling missing values in tabular data. Unlike traditional methods that often overlook the specific demands of imputation, TREB leverages…

Post-hoc explanation methods are gaining popularity for interpreting, understanding, and debugging neural networks. Most analyses using such methods explain decisions in response to inputs drawn from the test set. However, the test set may…

Abbreviations and contractions are commonly found in text across different domains. For example, doctors' notes contain many contractions that can be personalized based on their choices. Existing spelling correction models are not suitable…

Recently, there has been growing interest in the ability of Transformer-based models to produce meaningful embeddings of text with several applications, such as text similarity. Despite significant progress in the field, the explanations…