相关论文: ITL-LIME: Instance-Based Transfer Learning for Enh…

While accurate traffic forecasting is vital for Intelligent Transportation Systems (ITS), effectively communicating predicted conditions via natural language for human-centric decision support remains a challenge and is often handled…

In-context learning (ICL) is an important yet not fully understood ability of pre-trained large language models (LLMs). It can greatly enhance task performance using a few examples, termed demonstrations, without fine-tuning. Although…

Domain-specific intelligence demands specialized knowledge and sophisticated reasoning for problem-solving, posing significant challenges for large language models (LLMs) that struggle with knowledge hallucination and inadequate reasoning…

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…

Continuous-time reinforcement learning (CTRL) provides a natural framework for sequential decision-making in dynamic environments where interactions evolve continuously over time. While CTRL has shown growing empirical success, its ability…

Hydrocarbon prospect risking is a critical application in geophysics predicting well outcomes from a variety of data including geological, geophysical, and other information modalities. Traditional routines require interpreters to go…

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…

We introduce a new model-agnostic explanation technique which explains the prediction of any classifier called CLE. CLE gives an faithful and interpretable explanation to the prediction, by approximating the model locally using an…

Large Language Models (LLMs) have shown remarkable capabilities in natural language processing but exhibit significant performance gaps among different languages. Most existing approaches to address these disparities rely on pretraining or…

The emergent ability of Large Language Models to use a small number of examples to learn to perform in novel domains and tasks, also called in-context learning (ICL). In this work, we show that a much smaller model can be trained to perform…

In-context learning (ICL) is a type of prompting where a transformer model operates on a sequence of (input, output) examples and performs inference on-the-fly. In this work, we formalize in-context learning as an algorithm learning problem…

When applying multi-instance learning (MIL) to make predictions for bags of instances, the prediction accuracy of an instance often depends on not only the instance itself but also its context in the corresponding bag. From the viewpoint of…

Deep neural networks (DNNs) are successfully applied in a wide variety of music information retrieval (MIR) tasks. Such models are usually considered "black boxes", meaning that their predictions are not interpretable. Prior work on…

Estimating individualized treatment rules (ITRs) is fundamental to precision medicine, where the goal is to tailor treatment decisions to individual patient characteristics. While numerous methods have been developed for ITR estimation,…

Multiple instance learning (MIL) is a framework for weakly supervised classification, where labels are assigned to sets of instances, i.e., bags, rather than to individual data points. This paradigm has proven effective in tasks where…

Indecipherable black boxes are common in machine learning (ML), but applications increasingly require explainable artificial intelligence (XAI). The core of XAI is to establish transparent and interpretable data-driven algorithms. This work…

eXplainable Artificial Intelligence (XAI) aims at providing understandable explanations of black box models. In this paper, we evaluate current XAI methods by scoring them based on ground truth simulations and sensitivity analysis. To this…

Many practical applications require training of semantic segmentation models on unlabelled datasets and their execution on low-resource hardware. Distillation from a trained source model may represent a solution for the first but does not…

Hypothesis transfer learning (HTL) contrasts domain adaptation by allowing for a previous task leverage, named the source, into a new one, the target, without requiring access to the source data. Indeed, HTL relies only on a hypothesis…

Explainable Artificial Intelligence (XAI) aims to make machine learning models transparent and trustworthy, yet most current approaches communicate explanations visually or through text. This paper introduces an information theoretic…