Pesquisa de Doutorado da Veronica

 arXiv:2504.19667v1 [cs.LG] 28 Apr 2025    Large Language Models (LLMs) have shown remarkable capabilities across various domains, yet they struggle with knowledgeintensive tasks in areas that demand factual accuracy, such as in industrial automation and healthcare. Key limitations include their tendency to hallucinate, lack of source traceability (provenance), and challenges in timely knowledge updates. Retrieval Augmented Generation (RAG) techniques have attempted to address these issues by incorporating external knowledge, but they face their own limitations,.... Combining language models with knowledge graphs (GraphRAG) offers promising avenues for overcoming these deficits. However, a major challenge lies in creating such a knowledge graph in the first place.  Construir KG usando LLM só empurra o problema para o KG While language models (LLMs) have demonstrated impressive capabilities, they still have their limitations in knowledge-intensive tasks - especially i...

GeoRDF2Vec – Learning Location-Aware Entity Representations in Knowledge Graphs arXiv:2504.17099v1 [cs.LG] 23 Apr 2025  Many large knowledge graphs not only encode relational information between entities but also capture the geographic geometries of some or all of these entities. Prominent knowledge graphs such as DBpedia [17], YAGO [24], and Wikidata [32] contain geographic information on entities like places and buildings. Additionally, dedicated geographic knowledge graphs, such as KnowWhereGraph [14], WorldKG [8], and OSMh3KG [3], explicitly model geographic relationships. Exemplos de SKG 3. Böckling, M., Paulheim, H., Detzler, S.: A Planet Scale Spatial-Temporal Knowledge Graph Based On OpenStreetMap And H3 Grid. In: Geospatial Linked Data Workshop. arXiv (2024) 8. Dsouza, A., Tempelmeier, N., Yu, R., Gottschalk, S., Demidova, E.: WorldKG: A World-Scale Geographic Knowledge Graph. In: Proceedings of the 30th ACM International Conference on Information & Knowledge Mana...

Resumo do professor Altigran sobre os comentários dos revisores Nosso principal problema é o revisor 4, vejam abaixo: Aspecto Revisor 1 Revisor 2 Revisor 3 Revisor 4 Novelty Novel solution Novel solution Novel problem & solution No novelty Relevance Highly relevant Highly relevant Mostly relevant Mostly irrelevant Impact Notable impact on narrow audience or small impact on broad audience Small impact on narrow audience Notable impact on narrow audience or small impact on broad audience Little or no impact expected Technical Correctness No technical flaws Frequent major technical flaws Frequent minor or infrequent major technical flaws Frequent major technical flaws Clarity Generally well-written; clear in large part Difficult to understand; unclear in large part Understandable, but various parts could be clearer Difficult to understand; unclear in large part Comentários Nenhum Nenhum Nenhum Nenhum Expertise Parcialmente familiar: leu sobre tópicos relacionados Conhecedor: leu e tra...

Hogan, A., Dong, X.L., Vrandevci'c, D., & Weikum, G. (2025). Large Language Models, Knowledge Graphs and Search Engines: A Crossroads for Answering Users' Questions. A BACKGROUND A.1 Large Language Models LLMs capture contextual probabilities of tokens in the parameters of a large neural network, often following the Transformer architecture [44]. The model parameters are computed by two stages of training: unsupervised pre-training and supervised fine-tuning . LLMs can also benefit from inference-time (i.e., post-training) techniques, most notably, prompt engineering [26] and in-context learning [9]. The usual training objective is to predict the next token in a text sequence, repeatedly in an auto-regressive manner. As the original text is available, the ground-truth is known and this entire training process is completely unsupervised (or self-supervised, as it is sometimes phrased). Fine-tuning adopts a pre-trained LLM as a foundational model and adapts it for a sui...

Hogan, A., Dong, X.L., Vrandevci'c, D., & Weikum, G. (2025). Large Language Models, Knowledge Graphs and Search Engines: A Crossroads for Answering Users' Questions. 3 THE PERSPECTIVE OF INFORMATION-SEEKING USERS Todas as categorias podem estar presentes em processos de tomada de decisão Facts: Users seek objective, verifiable information that may be satisfied by a simple answer: a name, number, list, table, etc. Algumas variam com o tempo, outras exploram várias arestas (caminhos). Explanations: Users seek an explanation as to what something is, what caused it, what properties it has, how it works, etc., based principally on objective criteria. Exploratory queries involve gaining initial understanding into an unfamiliar topic, or further understanding into a familiar one. In this case, the user may not know precisely what they are looking for, but will rather hope to recognize it when they see it. Perguntas incompletas. Planning: Users seek information to help them tak...