Improving Factual Consistency for Knowledge-Grounded Dialogue Systems via Knowledge Enhancement and Alignment [PDF]
arXiv, 2023 Pretrained language models (PLMs) based knowledge-grounded dialogue systems are prone to generate responses that are factually inconsistent with the provided knowledge source. In such inconsistent responses, the dialogue models fail to accurately express the external knowledge they rely upon. Inspired by previous work which identified that feed-forward
arxiv
Measuring and repairing inconsistency in probabilistic knowledge bases [PDF]
, 2011 In this paper we present a family of measures aimed at determining the amount of inconsistency in probabilistic knowledge bases. Our approach to measuring inconsistency is graded in the sense that we consider minimal adjustments in the degrees of ...
Muiño, David Picado
core +1 more source
Knowledge Representation and Inference for Analysis and Design of Database and Tabular Rule-Based Systems [PDF]
Computer Science, 2001 Rulebased systems constitute a powerful tool for specification of knowledge in design and implementation of knowledge based systems. They provide also a universal programming paradigm for domains such as intelligent control, decision support, situation ...
Antoni Ligeza
doaj
KGQuiz: Evaluating the Generalization of Encoded Knowledge in Large Language Models [PDF]
arXiv, 2023 Large language models (LLMs) demonstrate remarkable performance on knowledge-intensive tasks, suggesting that real-world knowledge is encoded in their model parameters. However, besides explorations on a few probing tasks in limited knowledge domains, it is not well understood how to evaluate LLMs' knowledge systematically and how well their knowledge ...
arxiv
Towards Consistency Analysis Between Formal and Informal Software Architecture Artefacts [PDF]
, 2019 Documenting the architecture of a software system is important, especially to capture reasoning and design decisions. A lot of tacit knowledge can easily get lost when the documentation is incomplete, resulting in threats for the software system’s ...
Keim, Jan +2 more
core +2 more sources
Interpretability in neural networks towards universal consistency
International Journal of Cognitive Computing in Engineering, 2021 In the challenge of Artificial Intelligence in processing semantically evaluable information, the application of deep learning techniques depends not only on the algorithms, but also on the principles that explain how they work.
Dionéia Motta Monte-Serrat +1 more
doaj
Prediction of Physical Health (the Risk of Developing Diabetes) based on Social, Cultural, and Economic Capitals in Tabriz [PDF]
پژوهشهای راهبردی مسائل اجتماعی ایران, 2019 Introduction Health is not essentially a biological concept and instead, it includes the socio-psychological aspects. Moreover, health is not a personal theme and it is rooted in the structure of the society.
Abrahim Irannejad, +2 more
doaj +1 more source
A Knowledge Graph-Based Consistency Detection Method for Network Security Policies
Applied SciencesNetwork security policy is regarded as a guideline for the use and management of the network environment, which usually formulates various requirements in the form of natural language.
Yaang Chen +6 more
doaj +1 more source
Web ontology representation and reasoning via fragments of set theory
, 2015 In this paper we use results from Computable Set Theory as a means to represent and reason about description logics and rule languages for the semantic web.
A Formisano +8 more
core +1 more source
Journal of Integrative Bioinformatics, 2013 In systems biology, quantitative experimental data is the basis of building mathematical models. In most of the cases, they are stored in Excel files and hosted locally.
Shi Lei +8 more
doaj +1 more source