Related papers: OASYS: Domain-Agnostic Automated System for Constr…

Machine Learning-as-a-Service systems (MLaaS) have been largely developed for cybersecurity-critical applications, such as detecting network intrusions and fake news campaigns. Despite effectiveness, their robustness against adversarial…

AI safety has emerged as a critical priority as these systems are increasingly deployed in real-world applications. We propose the first domain-agnostic AI safety ensuring framework that achieves strong safety guarantees while preserving…

Despite the impressive performance of large language models (LLMs) in general domains, they often underperform in specialized domains. Existing approaches typically rely on data synthesis methods and yield promising results by using…

Previous text-to-SQL datasets and systems have primarily focused on user questions with clear intentions that can be answered. However, real user questions can often be ambiguous with multiple interpretations or unanswerable due to a lack…

The paradigm of training models on massive data without label through self-supervised learning (SSL) and finetuning on many downstream tasks has become a trend recently. However, due to the high training costs and the unconsciousness of…

AI systems have seen significant adoption in various domains. At the same time, further adoption in some domains is hindered by inability to fully trust an AI system that it will not harm a human. Besides the concerns for fairness, privacy,…

Clarifying user needs is essential for existing task-oriented dialogue systems. However, in real-world applications, developers can never guarantee that all possible user demands are taken into account in the design phase. Consequently,…

Open-domain neural dialogue models have achieved high performance in response ranking and evaluation tasks. These tasks are formulated as a binary classification of responses given in a dialogue context, and models generally learn to make…

The contribution of this paper is fourfold. The first contribution is a novel, generic method for automatic ground truth generation of camera-captured document images (books, magazines, articles, invoices, etc.). It enables us to build…

Web semantic access in specific domains calls for specialized search engines with enhanced semantic querying and indexing capacities, which pertain both to information retrieval (IR) and to information extraction (IE). A rich linguistic…

Natural language understanding involves reading between the lines with implicit background knowledge. Current systems either rely on pre-trained language models as the sole implicit source of world knowledge, or resort to external knowledge…

Open-retrieval question answering systems are generally trained and tested on large datasets in well-established domains. However, low-resource settings such as new and emerging domains would especially benefit from reliable question…

Language agents have achieved considerable performance on various complex question-answering tasks by planning with external tools. Despite the incessant exploration in this field, existing language agent systems still struggle with costly,…

Space agencies execute complex satellite operations that need to be supported by the technical knowledge contained in their extensive information systems. Knowledge bases (KB) are an effective way of storing and accessing such information…

Search-based Software Testing (SBST) can automatically generate test cases to search for requirements violations. Unlike manual test case development, it can generate a substantial number of test cases in a limited time. However, SBST does…

While large language models (LLMs) have demonstrated remarkable performance on high-level semantic tasks, they often struggle with fine-grained, token-level understanding and structural reasoning--capabilities that are essential for…

Large language models (LLMs) often have a fixed knowledge cutoff, limiting their accuracy on emerging information. We present ALAS (Autonomous Learning Agent System), a modular pipeline that continuously updates an LLM's knowledge with…

Explainability has become a crucial non-functional requirement to enhance transparency, build user trust, and ensure regulatory compliance. However, translating explanation needs expressed in user feedback into structured requirements and…

It is now widely recognized that ontologies, are one of the fundamental cornerstones of knowledge-based systems. What is lacking, however, is a currently accepted strategy of how to build ontology; what kinds of the resources and techniques…

Ontology-based knowledge graphs (KG) are desirable for effective knowledge management and reuse in various decision making scenarios, including design. Creating and populating extensive KG based on specific ontological models can be highly…