5 papers
ReFract: Benchmarking Perspective Awareness in Language Model Agents with Text World Models
Hainiu Xu, Vítor N. Lourenço, Mohnish Dubey +7
Large Language Model (LLM) agents are increasingly deployed in high-stakes settings such as industrial maintenance and equipment fault troubleshooting, where workers occupy a varie…
KG-CRAFT: Knowledge Graph-based Contrastive Reasoning with LLMs for Enhancing Automated Fact-checking
Vítor N. Lourenço, Aline Paes, Tillman Weyde +2
Claim verification is a core component of automated fact-checking systems, aimed at determining the truthfulness of a statement by assessing it against reliable evidence sources su…
Exploring Content and Social Connections of Fake News with Explainable Text and Graph Learning
Vítor N. Lourenço, Aline Paes, Tillman Weyde
The global spread of misinformation and concerns about content trustworthiness have driven the development of automated fact-checking systems. Since false information often exploit…
An Explainable Natural Language Framework for Identifying and Notifying Target Audiences In Enterprise Communication
Vítor N. Lourenço, Mohnish Dubey, Yunfei Bai +2
In large-scale maintenance organizations, identifying subject matter experts and managing communications across complex entities relationships poses significant challenges -- inclu…
Hierarchy-of-Visual-Words: a Learning-based Approach for Trademark Image Retrieval
Vítor N. Lourenço, Gabriela G. Silva, Leandro A. F. Fernandes
In this paper, we present the Hierarchy-of-Visual-Words (HoVW), a novel trademark image retrieval (TIR) method that decomposes images into simpler geometric shapes and defines a de…