Related papers: Model Assertions for Monitoring and Improving ML M…
Autonomous systems that rely on Machine Learning (ML) utilize online fault tolerance mechanisms, such as runtime monitors, to detect ML prediction errors and maintain safety during operation. However, the lack of human-interpretable…
Organizations rely heavily on time series metrics to measure and model key aspects of operational and business performance. The ability to reliably detect issues with these metrics is imperative to identifying early indicators of major…
Sensor-driven systems are increasingly ubiquitous: they provide both data and information that can facilitate real-time decision-making and autonomous actuation, as well as enabling informed policy choices by service providers and…
Lehman's Laws teach us that a software system will become progressively less satisfying to its users over time, unless it is continually adapted to meet new needs. Understanding software maintenance can potentially relieve many of the pains…
Nowadays, we are witnessing a wide adoption of Machine learning (ML) models in many safety-critical systems, thanks to recent breakthroughs in deep learning and reinforcement learning. Many people are now interacting with systems based on…
The desire to use reinforcement learning in safety-critical settings has inspired a recent interest in formal methods for learning algorithms. Existing formal methods for learning and optimization primarily consider the problem of…
The deployment of pre-trained perception models in novel environments often leads to performance degradation due to distributional shifts. Although recent artificial intelligence approaches for metacognition use logical rules to…
Detecting anomalies over real-world datasets remains a challenging task. Data annotation is an intensive human labor problem, particularly in sequential datasets, where the start and end time of anomalies are not known. As a result, data…
Machine Learning (ML) is now used in a range of systems with results that are reported to exceed, under certain conditions, human performance. Many of these systems, in domains such as healthcare , automotive and manufacturing, exhibit high…
Context: An increasing demand is observed in various domains to employ Machine Learning (ML) for solving complex problems. ML models are implemented as software components and deployed in Machine Learning Software Systems (MLSSs). Problem:…
Multi-turn tool-calling LLMs (models capable of invoking external APIs or tools across several user turns) have emerged as a key feature in modern AI assistants, enabling extended dialogues from benign tasks to critical business, medical,…
High-risk industries like nuclear and aviation use real-time monitoring to detect dangerous system conditions. Similarly, Large Language Models (LLMs) need monitoring safeguards. We propose a real-time framework to predict harmful AI…
Reasoning in Large Language Models (LLMs) poses a challenge for oversight as many misaligned behaviors do not surface until reasoning concludes. To address this, we introduce Behavior Cue Reasoning for making LLM reasoning more controllable…
Machine Learning (ML) is an expressive framework for turning data into computer programs. Across many problem domains -- both in industry and policy settings -- the types of computer programs needed for accurate prediction or optimal…
The proliferation of automated data collection schemes and the advances in sensorics are increasing the amount of data we are able to monitor in real-time. However, given the high annotation costs and the time required by quality…
Human educators possess an intrinsic ability to anticipate and seek educational explanations from students, which drives them to pose thought-provoking questions when students cannot articulate these explanations independently. We aim to…
Addressing the reproducibility crisis in artificial intelligence through the validation of reported experimental results is a challenging task. It necessitates either the reimplementation of techniques or a meticulous assessment of papers…
Large language models (LLMs) have shown remarkable adaptability to diverse tasks, by leveraging context prompts containing instructions, or minimal input-output examples. However, recent work revealed they also exhibit label bias -- an…
Software organizations are increasingly incorporating machine learning (ML) into their product offerings, driving a need for new data management tools. Many of these tools facilitate the initial development of ML applications, but…
This paper presents our findings for using activity modeling for simulation (validation), model checking (verification), and execution purposes. Each is needed to tackle system complexity and further research into behavioral modeling. We…