Related papers: Ontolearn-A Framework for Large-scale OWL Class Ex…
The eXtensible Markup Language (XML) can be used as data exchange format in different domains. It allows different parties to exchange data by providing common understanding of the basic concepts in the domain. XML covers the syntactic…
The prevailing paradigm for improving large language models relies on offline training with human annotations or simulated environments, leaving the rich experience accumulated during real-world deployment entirely unexploited. We propose…
Query optimization has been studied using machine learning, reinforcement learning, and, more recently, graph-based convolutional networks. Ontology, as a structured, information-rich knowledge representation, can provide context,…
Zero-shot learning (ZSL) is a popular research problem that aims at predicting for those classes that have never appeared in the training stage by utilizing the inter-class relationship with some side information. In this study, we propose…
Large Language Models (LLMs) exploit fine-tuning as a technique to adapt to diverse goals, thanks to task-specific training data. Task specificity should go hand in hand with domain orientation, that is, the specialization of an LLM to…
Large language models (LLMs) have become the foundation of many applications, leveraging their extensive capabilities in processing and understanding natural language. While many open-source LLMs have been released with technical reports,…
This paper presents an ontology-aware pretrained language model (OPAL) for end-to-end task-oriented dialogue (TOD). Unlike chit-chat dialogue models, task-oriented dialogue models fulfill at least two task-specific modules: dialogue state…
Despite the large number of patients in Electronic Health Records (EHRs), the subset of usable data for modeling outcomes of specific phenotypes are often imbalanced and of modest size. This can be attributed to the uneven coverage of…
Machine unlearning has emerged as a critical capability for addressing privacy, safety, and regulatory concerns in large language models (LLMs). Existing methods operate at the sequence level, applying uniform updates across all tokens…
Scalable learning for planning research generally involves juggling between different programming languages for handling learning and planning modules effectively. Interpreted languages such as Python are commonly used for learning routines…
Feature model are widely used to capture commonalities and variabilities of artefacts in Software Product Line (SPL). Several studies have discussed the formal representation of feature diagram using ontologies with different styles of…
Ontology learning (OL) is the process of automatically generating an ontological knowledge base from a plain text document. In this paper, we propose a new ontology learning approach and tool, called DLOL, which generates a knowledge base…
The ability of Large Language Models (LLMs) to perform reasoning tasks such as deduction has been widely investigated in recent years. Yet, their capacity to generate proofs-faithful, human-readable explanations of why conclusions…
Vision-language models (VLMs) such as CLIP exhibit strong Out-of-distribution (OOD) detection capabilities by aligning visual and textual representations. Recent CLIP-based test-time adaptation methods further improve detection performance…
Large Language Models (LLMs) excel at both informal and formal (e.g. Lean 4) mathematical reasoning but still struggle with autoformalisation, the task of transforming informal into formal mathematical statements. Autoformalisation helps…
The Object Constraint Language (OCL) has been widely used in the modeling community to complement software models for precisely defining constraints and business rules for the modeled systems. There is a limited number of tools supporting…
As large language models (LLMs) are trained on massive datasets, they have raised significant privacy and ethical concerns due to their potential to inadvertently retain sensitive information. Unlearning seeks to selectively remove specific…
Ontologies are essential for structuring domain knowledge, improving accessibility, sharing, and reuse. However, traditional ontology construction relies on manual annotation and conventional natural language processing (NLP) techniques,…
Text-rich document understanding (TDU) requires comprehensive analysis of documents containing substantial textual content and complex layouts. While Multimodal Large Language Models (MLLMs) have achieved fast progress in this domain,…
Obtaining a single-vector representation from a Large Language Model's (LLM) token-level outputs is a critical step for nearly all sentence-level tasks. However, standard pooling methods like mean or max aggregation treat tokens as an…