Related papers: Technical report of "The Knowledge Base Paradigm A…
We investigate a multi-agent model of firms in an R\&D network. Each firm is characterized by its knowledge stock $x_{i}(t)$, which follows a non-linear dynamics. It can grow with the input from other firms, i.e., by knowledge transfer, and…
Behavior cloning has shown success in many sequential decision-making tasks by learning from expert demonstrations, yet they can be very sample inefficient and fail to generalize to unseen scenarios. One approach to these problems is to…
We address the problem of propositional logic-based abduction, i.e., the problem of searching for a best explanation for a given propositional observation according to a given propositional knowledge base. We give a general algorithm, based…
When should we delegate decisions to AI systems? While the value alignment literature has developed techniques for shaping AI values, less attention has been paid to how to determine, under uncertainty, when imperfect alignment is good…
Automated text generation requires a underlying knowledge base from which to generate, which is often difficult to produce. Software documentation is one domain in which parts of this knowledge base may be derived automatically. In this…
The integration of artificial intelligence (AI) into human decision-making processes at the workplace presents both opportunities and challenges. One promising approach to leverage existing complementary capabilities is allowing humans to…
The Domain Name System (DNS) is one of the most important components of the Internet infrastructure. DNS relies on a delegation-based architecture, where resolution of names to their IP addresses requires resolving the names of the servers…
Despite the advances in large language models (LLMs), how they use their knowledge for reasoning is not yet well understood. In this study, we propose a method that deconstructs complex real-world questions into a graph, representing each…
Research in the field of electronic signature confirmation has been active for some 20 years now. Unfortunately present certificate-based solutions also come from that age when no-one knew about online data transmission. The official…
A major difficulty in developing and maintaining very large knowledge bases originates from the variety of forms in which knowledge is made available to the KB builder. The objective of this research is to bring together two complementary…
Knowledge-grounded dialogue is a task of generating an informative response based on both the dialogue history and external knowledge source. In general, there are two forms of knowledge: manually annotated knowledge graphs and knowledge…
In the past years, software reverse engineering dealt with source code understanding. Nowadays, it is levered to software requirements abstract level, supported by feature model notations, language independent, and simpler than the source…
Concept Bottleneck Models (CBMs) use a set of human-interpretable concepts to predict the final task label, enabling domain experts to not only validate the CBM's predictions, but also intervene on incorrect concepts at test time. However,…
While enabling large language models to implement function calling (known as APIs) can greatly enhance the performance of Large Language Models (LLMs), function calling is still a challenging task due to the complicated relations between…
In this paper, we consider sequential dynamic team decision problems with nonclassical information structures. First, we address the problem from the point of view of a ``manager" who seeks to derive the optimal strategy of the team in a…
In this paper we present the process of Knowledge Elicitation through a structured questionnaire technique. This is an effort to depict a problem domain as Investigation of factors affecting taskforce productivity. The problem has to be…
The modern Internet is highly dependent on trust communicated via certificates. However, in some cases, certificates become untrusted, and it is necessary to revoke them. In practice, the problem of secure revocation is still open.…
Intelligent information systems that contain emergent elements often encounter trust problems because results do not get sufficiently explained and the procedure itself can not be fully retraced. This is caused by a control flow depending…
An advantage of scientific workflow systems is their ability to collect runtime provenance information as an execution trace. Traces include the computation steps invoked as part of the workflow run along with the corresponding data…
A compelling approach to complex question answering is to convert the question to a sequence of actions, which can then be executed on the knowledge base to yield the answer, aka the programmer-interpreter approach. Use similar training…