相关论文: InterpretML: A Unified Framework for Machine Learn…

The widespread adoption of complex machine learning models in high-stakes domains has brought the "black-box" problem to the forefront of responsible AI research. This paper aims at addressing this issue by improving the Explainable…

Soft prompts have been popularized as a cheap and easy way to improve task-specific LLM performance beyond few-shot prompts. Despite their origin as an automated prompting method, however, soft prompts and other trainable prompts remain a…

We develop KnowThyself, an agentic assistant that advances large language model (LLM) interpretability. Existing tools provide useful insights but remain fragmented and code-intensive. KnowThyself consolidates these capabilities into a…

YAMLE: Yet Another Machine Learning Environment is an open-source framework that facilitates rapid prototyping and experimentation with machine learning (ML) models and methods. The key motivation is to reduce repetitive work when…

Machine learning (ML) in general and deep learning (DL) in particular has become an extremely popular tool in several vision applications (like object detection, super resolution, segmentation, object tracking etc.). Almost in parallel, the…

The field of machine learning has seen tremendous progress in recent years, with deep learning models delivering exceptional performance across a range of tasks. However, these models often come at the cost of interpretability, as they…

Interpretability methods for neural networks are difficult to evaluate because we do not understand the black-box models typically used to test them. This paper proposes a framework in which interpretability methods are evaluated using…

Understanding the internal representations of large language models (LLMs) can help explain models' behavior and verify their alignment with human values. Given the capabilities of LLMs in generating human-understandable text, we propose…

Many risk-sensitive applications require Machine Learning (ML) models to be interpretable. Attempts to obtain interpretable models typically rely on tuning, by trial-and-error, hyper-parameters of model complexity that are only loosely…

The integration of artificial intelligence into business processes has significantly enhanced decision-making capabilities across various industries such as finance, healthcare, and retail. However, explaining the decisions made by these AI…

Summary Brain Predictability toolbox (BPt) represents a unified framework of machine learning (ML) tools designed to work with both tabulated data (in particular brain, psychiatric, behavioral, and physiological variables) and neuroimaging…

Interpretability methods aim to help users build trust in and understand the capabilities of machine learning models. However, existing approaches often rely on abstract, complex visualizations that poorly map to the task at hand or require…

The financial industry faces a significant challenge modeling and risk portfolios: balancing the predictability of advanced machine learning models, neural network models, and explainability required by regulatory entities (such as Office…

Several researchers have argued that a machine learning system's interpretability should be defined in relation to a specific agent or task: we should not ask if the system is interpretable, but to whom is it interpretable. We describe a…

Recent large language models (LLMs) have demonstrated remarkable prediction performance for a growing array of tasks. However, their proliferation into high-stakes domains (e.g. medicine) and compute-limited settings has created a…

Neural Machine Translation (NMT) models have shown remarkable performance but remain largely opaque in their decision making processes. The interpretability of these models, especially their internal attention mechanisms, is critical for…

Time series forecasting enables early warning and has driven asset performance management from traditional planned maintenance to predictive maintenance. However, the lack of interpretability in forecasting methods undermines users' trust…

Trustworthy machine learning is driving a large number of ML community works in order to improve ML acceptance and adoption. The main aspect of trustworthy machine learning are the followings: fairness, uncertainty, robustness,…

We introduce OmniXAI (short for Omni eXplainable AI), an open-source Python library of eXplainable AI (XAI), which offers omni-way explainable AI capabilities and various interpretable machine learning techniques to address the pain points…

From self-driving vehicles and back-flipping robots to virtual assistants who book our next appointment at the hair salon or at that restaurant for dinner - machine learning systems are becoming increasingly ubiquitous. The main reason for…