Related papers: Truth Discovery to Resolve Object Conflicts in Lin…

Misinformation detection models often rely on superficial cues (i.e., \emph{shortcuts}) that correlate with misinformation in training data but fail to generalize to the diverse and evolving nature of real-world misinformation. This issue…

The Linked Data community is focused on integrating Resource Description Framework (RDF) data sets into a single unified representation known as the Web of Data. The Web of Data can be traversed by both man and machine and shows promise as…

Deepfake has taken the world by storm, triggering a trust crisis. Current deepfake detection methods are typically inadequate in generalizability, with a tendency to overfit to image contents such as the background, which are frequently…

We initiate an investigation of learning tasks in a setting where the learner is given access to two competing provers, only one of which is honest. Specifically, we consider the power of such learners in assessing purported properties of…

Grounded text generation systems often generate text that contains factual inconsistencies, hindering their real-world applicability. Automatic factual consistency evaluation may help alleviate this limitation by accelerating evaluation…

As large language models (LLMs) are more frequently used in retrieval-augmented generation pipelines, it is increasingly relevant to study their behavior under knowledge conflicts. Thus far, the role of the source of the retrieved…

We introduce a novel task, called Generalized Relation Discovery (GRD), for open-world relation extraction. GRD aims to identify unlabeled instances in existing pre-defined relations or discover novel relations by assigning instances to…

Large Language Models (LLMs) have exhibited impressive generation capabilities, but they suffer from hallucinations when solely relying on their internal knowledge, especially when answering questions that require less commonly known…

Large language models (LLMs) are known to struggle with consistently generating truthful responses. While various representation intervention techniques have been proposed, these methods typically apply a universal representation correction…

The Linked Data principles provide a decentral approach for publishing structured data in the RDF format on the Web. In contrast to structured data published in relational databases where a key is often provided explicitly, finding a set of…

Large language models (LLMs) may generate text that lacks consistency with human knowledge, leading to factual inaccuracies or \textit{hallucination}. Existing research for evaluating the factuality of LLMs involves extracting fact claims…

The Semantic Web technologies have been used in the Internet of Things (IoT) to facilitate data interoperability and address data heterogeneity issues. The Resource Description Framework (RDF) model is employed in the integration of IoT…

This document defines extensions of the RDF data model and of the SPARQL query language that capture an alternative approach to represent statement-level metadata. While this alternative approach is backwards compatible with RDF reification…

We investigate the problem of aligning two RDF databases, an essential problem in understanding the evolution of ontologies. Our approaches address three fundamental challenges: 1) the use of "blank" (null) names, 2) ontology changes in…

The most important problem that has emerged after twenty years of popular internet usage is that of fact-checking at scale. This problem is experienced acutely in both of the major internet application platform types, web search and social…

Multiple hypothesis testing, a situation when we wish to consider many hypotheses, is a core problem in statistical inference that arises in almost every scientific field. In this setting, controlling the false discovery rate (FDR), which…

Resolving knowledge conflicts is a crucial challenge in Question Answering (QA) tasks, as the internet contains numerous conflicting facts and opinions. While some research has made progress in tackling ambiguous settings where multiple…

Federated Learning (FL) has gained prominence in machine learning applications across critical domains by enabling collaborative model training without centralized data aggregation. However, FL frameworks that protect privacy often…

Despite the growing development of long-context large language models (LLMs), data-centric approaches relying on synthetic data have been hindered by issues related to faithfulness, which limit their effectiveness in enhancing model…

The increased focus on misinformation has spurred development of data and systems for detecting the veracity of a claim as well as retrieving authoritative evidence. The Fact Extraction and VERification (FEVER) dataset provides such a…