Related papers: Inconsistent Databases and Argumentation Framework…
Counterfactual reasoning -- the practice of asking ``what if'' by varying inputs and observing changes in model behavior -- has become central to interpretable and fair AI. This thesis develops frameworks that use counterfactuals to…
Consistent Query Answering (CQA) is the problem of computing from a database the answers to a query that are consistent with respect to certain integrity constraints that the database, as a whole, may fail to satisfy. Consistent answers…
Deep neural networks represent the state of the art in machine learning in a growing number of fields, including vision, speech and natural language processing. However, recent work raises important questions about the robustness of such…
High-stakes decision systems increasingly require structured justification, traceability, and auditability to ensure accountability and regulatory compliance. Formal arguments commonly used in the certification of safety-critical systems…
In this work, answer-set programs that specify repairs of databases are used as a basis for solving computational and reasoning problems about causes for query answers from databases.
For several reasons a database may not satisfy a given set of integrity constraints(ICs), but most likely most of the information in it is still consistent with those ICs; and could be retrieved when queries are answered. Consistent answers…
The structures for the expression of fault-tolerance provisions into the application software are the central topic of this dissertation. Structuring techniques provide means to control complexity, the latter being a relevant factor for the…
While recent works have been considerably improving the quality of the natural language explanations (NLEs) generated by a model to justify its predictions, there is very limited research in detecting and alleviating inconsistencies among…
Interpretable time series deep learning systems are often assessed by checking temporal consistency on explanations, implicitly treating this as evidence of robustness. We show that this assumption can fail: Predictions and explanations can…
From an inconsistent database non-trivial arguments may be constructed both for a proposition, and for the contrary of that proposition. Therefore, inconsistency in a logical database causes uncertainty about which conclusions to accept.…
Retrieval-Augmented Generation (RAG) systems often fail on multi-hop queries when the initial retrieval misses a bridge fact. Prior corrective approaches, such as Self-RAG, CRAG, and Adaptive-$k$, typically address this by \textit{adding}…
Consistent Query Answering (CQA) is an inconsistency-tolerant approach to data access in knowledge bases and databases. The goal of CQA is to provide meaningful (consistent) answers to queries even in the presence of inconsistent…
AI-augmented data processing systems (DPSs) integrate large language models (LLMs) into query pipelines, allowing powerful semantic operations on structured and unstructured data. However, the reliability (a.k.a. trust) of these systems is…
Dung's abstract argumentation framework consists of a set of interacting arguments and a series of semantics for evaluating them. Those semantics partition the powerset of the set of arguments into two classes: extensions and…
Abstract argumentation frameworks (AFs) provide a formal setting to analyze many forms of reasoning with conflicting information. While the expressiveness of general infinite AFs make them a tempting tool for modeling many kinds of…
We study consistent query answering in relational databases. We consider an expressive class of schema constraints that generalizes both tuple-generating dependencies and equality-generating dependencies. We establish the complexity of…
Datasets may include errors, and specifically violations of integrity constraints, for various reasons. Standard techniques for ``minimal-cost'' database repairing resolve these violations by aiming for minimum change in the data, and in…
Consider the problem of imputing missing values in a dataset. One the one hand, conventional approaches using iterative imputation benefit from the simplicity and customizability of learning conditional distributions directly, but suffer…
Explainable artificial intelligence (XAI) has become increasingly important in decision-critical domains such as healthcare, finance, and law. Counterfactual (CF) explanations, a key approach in XAI, provide users with actionable insights…
Current adversarial attack research reveals the vulnerability of learning-based classifiers against carefully crafted perturbations. However, most existing attack methods have inherent limitations in cross-dataset generalization as they…