相关论文: Understanding Feedback Mechanisms in Machine Learn…
Computational notebooks are notoriously prone to reproducibility failures. By permitting out-of-order cell execution, notebooks accumulate hidden state and implicit dependencies that cause interactive executions to silently diverge from…
Jupyter Notebooks are an enormously popular tool for creating and narrating computational research projects. They also have enormous potential for creating reproducible scientific research artifacts. Capturing the complete state of a…
Modern machine learning systems use models trained on ever-growing corpora. Typically, metadata such as ownership, access control, or licensing information is ignored during training. Instead, to mitigate privacy risks, we rely on generic…
Jupyter notebooks represent a unique format for programming - a combination of code and Markdown with rich formatting, separated into individual cells. We propose to perceive a Jupyter Notebook cell as a simplified and raw version of a…
Machine unlearning aims to remove sensitive or undesired data from large language models. However, recent studies suggest that unlearning is often shallow, claiming that removed knowledge can easily be recovered. In this work, we critically…
Abstract Machine understanding of questions is tightly related to recognition of articulation in the context of the computational capabilities of an underlying processing algorithm. In this paper a mathematical model to capture and…
Model selection is a necessary step in unsupervised machine learning. Despite numerous criteria and metrics, model selection remains subjective. A high degree of subjectivity may lead to questions about repeatability and reproducibility of…
In this paper, we study the task of selecting the optimal response given a user and system utterance history in retrieval-based multi-turn dialog systems. Recently, pre-trained language models (e.g., BERT, RoBERTa, and ELECTRA) showed…
Human feedback data is a critical component in developing language models. However, collecting this feedback is costly and ultimately not scalable. Inspired by the way human interlocutors provide spontaneous unsolicited feedback to each…
The research of artificial intelligence is undergoing a paradigm shift from prioritizing model innovations over benchmark scores towards emphasizing problem definition and rigorous real-world evaluation. As the field enters the "second…
Pre-trained language models derive substantial linguistic and factual knowledge from the massive corpora on which they are trained, and prompt engineering seeks to align these models to specific tasks. Unfortunately, existing prompt…
In the era of data-driven intelligence, the paradox of data abundance and annotation scarcity has emerged as a critical bottleneck in the advancement of machine learning. This paper gives a detailed overview of Active Learning (AL), which…
Researchers have been highly active to investigate the classical machine learning workflow and integrate best practices from the software engineering lifecycle. However, deep learning exhibits deviations that are not yet covered in this…
Any act of problem-solving combines prior knowledge, local search, and a third element that is less often discussed: the extraction of information from search to update understanding. I propose a model of mathematical problem-solving as a…
Simulation workflow is a top-level model for the design and control of simulation process. It connects multiple simulation components with time and interaction restrictions to form a complete simulation system. Before the construction and…
Developing and fielding complex systems requires proof that they are reliably correct with respect to their design and operating requirements. Especially for autonomous systems which exhibit unanticipated emergent behavior, fully…
Explaining why a language model produces a particular output requires local, input-level explanations. Existing methods uncover global capability circuits (e.g., indirect object identification), but not why the model answers a specific…
Machine learning has the potential to fuel further advances in data science, but it is greatly hindered by an ad hoc design process, poor data hygiene, and a lack of statistical rigor in model evaluation. Recently, these issues have begun…
Many users struggle to notice when a more efficient workflow exists in feature-rich tools like Excel. Existing AI assistants offer help only after users describe their goals or problems, which can be effortful and imprecise. We present…
Linearising the dynamics of nonlinear mechanical systems is an important and open research area. A common approach is feedback linearisation, which is a nonlinear control method that transforms the input-output response of a nonlinear…