Related papers: Efficient Evidence Generation for Modal $\mu$-Calc…
This paper proposes a novel Bayesian active learning method for Bayesian model updating, which is termed as "Streamlined Bayesian Active Learning Cubature" (SBALC). The core idea is to approximate the log-likelihood function using Gaussian…
Expert specialization in Mixture-of-Experts (MoE) models remains poorly understood, with traditional evaluations conflating architectural load-balancing with functional specialization. We introduce DBES, a comprehensive diagnostic framework…
Providing Language Models (LMs) with relevant evidence in the context (either via retrieval or user-provided) can significantly improve their ability to provide better-grounded responses. However, recent studies have found that LMs often…
Probabilistic models analyze data by relying on a set of assumptions. Data that exhibit deviations from these assumptions can undermine inference and prediction quality. Robust models offer protection against mismatch between a model's…
ML models are increasingly deployed in settings with real world interactions such as vehicles, but unfortunately, these models can fail in systematic ways. To prevent errors, ML engineering teams monitor and continuously improve these…
Determining whether a given claim is supported by evidence is a fundamental NLP problem that is best modeled as Textual Entailment. However, given a large collection of text, finding evidence that could support or refute a given claim is a…
We report on an effort to develop methodologies for formal verification of parts of the Multi-Purpose Daemon (MPD) parallel process management system. MPD is a distributed collection of communicating processes. While the individual…
Bayesian evidence is a standard tool used for comparing the ability of different models to fit available data and is used extensively in cosmology. However, since the evidence calculation involves performing an integral of the likelihood…
The quality and correct functioning of software components embedded in electronic systems are of utmost concern especially for safety and mission-critical systems. Model-based testing and formal verification techniques can be employed to…
Many methods of estimating causal models do not provide estimates of confidence in the resulting model. In this work, a metric is proposed for validating the output of a causal model fit; the robustness of the model structure with resampled…
Commonsense generation aims at generating plausible everyday scenario description based on a set of provided concepts. Digging the relationship of concepts from scratch is non-trivial, therefore, we retrieve prototypes from external…
Finite element model updating is challenging because 1) the problem is oftentimes underdetermined while the measurements are limited and/or incomplete; 2) many combinations of parameters may yield responses that are similar with respect to…
This work utilizes the plethora of work on verification of sequential programs for the purpose of verifying concurrent programs. We reduce the verification of a concurrent program to a series of verification tasks of sequential programs.…
Pseudo-Labeling is a simple and effective approach to semi-supervised learning. It requires criteria that guide the selection of pseudo-labeled data. The latter have been shown to crucially affect pseudo-labeling's generalization…
Real-world fact verification task aims to verify the factuality of a claim by retrieving evidence from the source document. The quality of the retrieved evidence plays an important role in claim verification. Ideally, the retrieved evidence…
Model explanations can be valuable for interpreting and debugging predictive models. We study a specific kind called Concept Explanations, where the goal is to interpret a model using human-understandable concepts. Although popular for…
This paper develops new insights into quantitative methods for the validation of computational model prediction. Four types of methods are investigated, namely classical and Bayesian hypothesis testing, a reliability-based method, and an…
Bounded Model Checking (BMC) is a powerful technique for proving unsafety. However, finding deep counterexamples that require a large bound is challenging for BMC. On the other hand, acceleration techniques compute "shortcuts" that…
In Bayesian hypothesis testing, evidence for a statistical model is quantified by the Bayes factor, which represents the relative likelihood of observed data under that model compared to another competing model. In general, computing Bayes…
Mistake detection in procedural tasks is essential for building intelligent systems that support learning and task execution. Existing approaches primarily analyze how an action is performed, while overlooking what it produces, i.e., the…