Related papers: Efficiently Computing Compact Formal Explanations
We present a framework for performing efficient regression in general metric spaces. Roughly speaking, our regressor predicts the value at a new point by computing a Lipschitz extension --- the smoothest function consistent with the…
Neural network architectures in natural language processing often use attention mechanisms to produce probability distributions over input token representations. Attention has empirically been demonstrated to improve performance in various…
With the increasing application of deep learning in mission-critical systems, there is a growing need to obtain formal guarantees about the behaviors of neural networks. Indeed, many approaches for verifying neural networks have been…
While large-scale pretrained language models have obtained impressive results when fine-tuned on a wide variety of tasks, they still often suffer from overfitting in low-resource scenarios. Since such models are general-purpose feature…
A central challenge in mechanism design is to identify mechanisms whose performance is robust under uncertainty about the environment. The maxmin optimality criterion is commonly used for this purpose, but it often yields a large and…
In this work we focus our attention on distributed optimization problems in the context where the communication time between the server and the workers is non-negligible. We obtain novel methods supporting bidirectional compression (both…
Explainable Artificial Intelligence (XAI) techniques hold significant potential for enhancing the causal discovery process, which is crucial for understanding complex systems in areas like healthcare, economics, and artificial intelligence.…
Distributed systems adopt weak consistency to ensure high availability and low latency, but state convergence is hard to guarantee due to conflicts. Experts carefully design replicated data types (RDTs) that resemble sequential data types…
Reduced-precision data formats are crucial for cost-effective serving of large language models (LLMs). While numerous reduced-precision formats have been introduced thus far, they often require intrusive modifications to the software…
Most of the work on interpretable machine learning has focused on designing either inherently interpretable models, which typically trade-off accuracy for interpretability, or post-hoc explanation systems, whose explanation quality can be…
Building on existing work with Hyperblocks, which classify data using minimum and maximum bounds for each attribute, we focus on enhancing interpretability, decreasing training time, and reducing model complexity without sacrificing…
This work introduces VERSE, a methodology for analyzing and improving Vision-Language Models applied to Visually-rich Document Understanding by exploring their visual embedding space. VERSE enables the visualization of latent…
Artificial intelligence explanations can make complex predictive models more comprehensible. To be effective, however, they should anticipate and mitigate possible misinterpretations, e.g., arising when users infer incorrect information…
The rationale behind a deep learning model's output is often difficult to understand by humans. EXplainable AI (XAI) aims at solving this by developing methods that improve interpretability and explainability of machine learning models.…
We study policy evaluation of offline contextual bandits subject to unobserved confounders. Sensitivity analysis methods are commonly used to estimate the policy value under the worst-case confounding over a given uncertainty set. However,…
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…
Explainable Artificial Intelligence (XAI) has become critical in enhancing the transparency and trustworthiness of AI systems, especially as these systems are increasingly deployed in high-stakes domains such as healthcare and finance.…
Explainable AI (XAI) is an active research area to interpret a neural network's decision by ensuring transparency and trust in the task-specified learned models. Recently, perturbation-based model analysis has shown better interpretation,…
The quality of supervised fine-tuning (SFT) data is crucial for the performance of large multimodal models (LMMs), yet current data enhancement methods often suffer from factual errors and hallucinations due to inadequate visual perception.…
Explaining deep learning models operating on time series data is crucial in various applications of interest which require interpretable and transparent insights from time series signals. In this work, we investigate this problem from an…