Related papers: Studying the explanations for the automated predic…
When predictive models are used to support complex and important decisions, the ability to explain a model's reasoning can increase trust, expose hidden biases, and reduce vulnerability to adversarial attacks. However, attempts at…
The emergence of tools based on artificial intelligence has also led to the need of producing explanations which are understandable by a human being. In most approaches, the system is considered a black box, making it difficult to generate…
The use of complex machine learning models can make systems opaque to users. Machine learning research proposes the use of post-hoc explanations. However, it is unclear if they give users insights into otherwise uninterpretable models. One…
Explaining predictions based on multivariate time series data carries the additional difficulty of handling not only multiple features, but also time dependencies. It matters not only what happened, but also when, and the same feature could…
A systems quality is a major concern for development teams when it evolve. Understanding the effects of a loss of quality in the codebase is crucial to avoid side effects like the appearance of technical debt. Although the identification of…
The adoption of machine learning in high-stakes applications such as healthcare and law has lagged in part because predictions are not accompanied by explanations comprehensible to the domain user, who often holds the ultimate…
We introduce the notion of pointwise coverage to measure the explainability properties of machine learning classifiers. An explanation for a prediction is a definably simple region of the feature space sharing the same label as the…
Prediction of a machine's Remaining Useful Life (RUL) is one of the key tasks in predictive maintenance. The task is treated as a regression problem where Machine Learning (ML) algorithms are used to predict the RUL of machine components.…
We share observations and challenges from an ongoing effort to implement Explainable AI (XAI) in a domain-specific workflow for cybersecurity analysts. Specifically, we briefly describe a preliminary case study on the use of XAI for source…
While large language models (LLMs) have demonstrated strong capability in structured prediction tasks such as semantic parsing, few amounts of research have explored the underlying mechanisms of their success. Our work studies different…
We explore solutions for automated labeling of content in bug trackers and customer support systems. In order to do that, we classify content in terms of several criteria, such as priority or product area. In the first part of the paper, we…
As LLMs become increasingly proficient at producing human-like responses, there has been a rise of academic and industrial pursuits dedicated to flagging a given piece of text as "human" or "AI". Most of these pursuits involve modern NLP…
Link prediction (LP) is an important problem in network science and machine learning research. The state-of-the-art LP methods are usually evaluated in a uniform setup, ignoring several factors associated with the data and application…
Automated Program Repair (APR) agents leverage Large Language Models (LLMs) to autonomously diagnose and fix software bugs through reasoning, planning, and tool use. Despite impressive leaderboard gains on benchmarks such as SWE-bench,…
Nowadays, development teams often rely on tools such as Jira or Bugzilla to manage backlogs of issues to be solved to develop or maintain software. Although they relate to many different concerns (e.g., bug fixing, new feature development,…
After a review of linear imperfections and their causes, we discuss how to model them, the diagnostic equipment needed to monitor them, and the correction algorithms to fix the problem they cause. We first address linear systems - beam…
Human-in-the-loop aims to train an accurate prediction model with minimum cost by integrating human knowledge and experience. Humans can provide training data for machine learning applications and directly accomplish tasks that are hard for…
How predictable a word is can be quantified in two ways: using human responses to the cloze task or using probabilities from language models (LMs).When used as predictors of processing effort, LM probabilities outperform probabilities…
This text discusses several popular explanatory methods that go beyond the error measurements and plots traditionally used to assess machine learning models. Some of the explanatory methods are accepted tools of the trade while others are…
Recent language models have demonstrated proficiency in summarizing source code. However, as in many other domains of machine learning, language models of code lack sufficient explainability. Informally, we lack a formulaic or intuitive…