RURicardo Usbeck

Ricardo Usbeck

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Ricardo Usbeck has a total of 130 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Beyond Edge Addition: A Dataset for Information Extraction Incorporating New Instances, Types, and Relations

    by Sven Hertling, Cedric Möller, Nandana Mihindukulasooriya, Ricardo Usbeck

  • Open Access

    KGXL-Query: Extending SPARQL with Semantic Search and LLM Functionality for Question Answering over Heterogeneous Data

    by Tilahun Abedissa Taffa, Patrick Westphal, Debayan Banerjee, Ricardo Usbeck

    The quest to answer complex questions, those requiring both structured facts and contextual evidence from unstructured data, has shown a gap in knowledge systems: the incompatibility between symbolic and semantic inference. Knowledge Graphs (KGs) support formal, logically grounded querying via structured languages such as SPARQL. Conversely, LLMs (Large Language Models) and semantic text search offer broad knowledge coverage through vector-based similarity metrics. However, beyond using KGs for refining text or LLM results, and complementing missing information in KGs via LLMs or text search, there is less emphasis on accessing LLMs & semantic text search functionality through SPARQL. Moreover, existing Question Answering (QA) methods on heterogeneous data sources use RAG, data unification, and decompose-and-aggregate methods. The unifying approaches suffer from irreversible information loss; decomposition-driven methods are prone to cascading errors; and RAG methods lack explainability and are limited to shallow textual integration. Therefore, we introduce KGXL-Query, a new SPARQL functionality extension that embeds LLMs and semantic search directly into SPARQL, enabling hybrid inference where symbolic and non-symbolic methods coexist within a single, executable, and explainable framework. Additionally, KGXL-Query paves the way by transforming the question to leverage the model rather than altering the data to fit it. Our experiments on four heterogeneous QA datasets show that KGXL consistently outperforms existing methods across all four benchmarks.

  • Open Access

    STaRQ-Agent-Investigating Generalization in Knowledge Graph Question Answering via a Multi-Agent Collaborative Framework

    by Longquan Jiang, Debayan Banerjee, Ricardo Usbeck

    Generalization to different Knowledge Graphs (KGs) is a core challenge of Knowledge Graph Question Answering (KGQA). Current models struggle to adapt to unseen KGs due to their underlying heterogeneity. Most approaches depend on data-hungry methods, such as supervised fine-tuning and KG-specific few-shot demonstrations. These systems are limited in cross-KG generalization, and may exhibit hallucination problems, especially in low-resource or domain-specific scenarios. This paper presents STaRQ-Agent, an LLM-based multi-agent collaborative framework for the KGQA generalization problem. It comprises a core agent for SPARQL query generation, accompanied by three supportive agents for schema selection, template generation, and query refinement. This collaborative framework helps mitigate hallucination problems inherent in LLMs. STaRQ-Agent was evaluated on LC-QuAD 1.0, QALD-9, MetaQA, and MatKGQA datasets in few-shot and zero-shot settings. Experimental results demonstrate strong overall generalization across diverse KGs, without requiring high-quality annotated data, re-training, or fine-tuning. Specially, on LC-QuAD 1.0, QALD-9, and MetaQA, few-shot STaRQ-Agent outperforms the strongest baseline by 5.1%, 4.3%, and 0.7%, while zero-shot STaRQ-Agent shows only modest F1 drops of 8.7%, 12.3%, and 10.8%. Moreover, the state-of-the-art results on MatKGQA show its robust out-of-distribution generalization to novel KGs in low-resource specific domains.

  • Open Access

    DBLP QuAD 2.0: Scholarly Natural Questions from SPARQL

    by Tilahun Abedissa Taffa, Patrick Neises, Stefan Ollinger, Patrick Westphal, Marcel R. Ackermann, Debayan Banerjee, Ricardo Usbeck

  • Open Access

    ReportGRI: Automating GRI Alignment and Report Assessment

    by Aida Usmanova, Rana Abdullah, Debayan Banerjee, Markus Leippold, Ricardo Usbeck


  • Open Access

    NFDI4DS Shared Tasks for Scholarly Document Processing

    by Raia Abu Ahmad, Rana Abdulla, Tilahun Abedissa Taffa, Soeren Auer, Hamed Babaei Giglou, Ekaterina Borisova, Zongxiong Chen, Stefan Dietze, Jennifer Dsouza, Mayra Elwes, et al.

    Shared tasks are powerful tools for advancing research through community-based standardised evaluation. As such, they play a key role in promoting findable, accessible, interoperable, and reusable (FAIR), as well as transparent and reproducible research practices. This paper presents an updated overview of twelve shared tasks developed and hosted under the German National Research Data Infrastructure for Data Science and Artificial Intelligence (NFDI4DS) consortium, covering a diverse set of challenges in scholarly document processing. Hosted at leading venues, the tasks foster methodological innovations and contribute open-access datasets, models, and tools for the broader research community, which are integrated into the consortium's research data infrastructure.

  • Open Access

    HySQA: Hybrid Scholarly Question Answering

    by Tilahun Abedissa Taffa, Debayan Banerjee, Yaregal Assabie, Ricardo Usbeck

    Purpose: The heterogeneity of scholarly information in knowledge graphs (KGs) and unstructured textual sources poses challenges in building robust Scholarly Question Answering (SQA) systems. Existing datasets and models typically address a narrow spectrum, focusing exclusively on KGs or unstructured sources and limiting evaluation to simple factoid questions. This gap leaves current systems unable to answer complex, hybrid scholarly questions that require integrating evidence from multiple heterogeneous data sources. Methodology: We introduce HySQA (Hybrid Scholarly Question Answering), a large-scale benchmarking dataset containing hybrid questions over scholarly KGs and Wikipedia text. HySQA contains complex questions that need to traverse facts across structured and unstructured sources. We also develop a baseline model that adaptively decomposes each question into sub-questions, identifies their answer sources, retrieves relevant information from SKGs and Wikipedia, and generates an answer using a hybrid augmented answer generation framework. Findings: The experimental results show that integrating static and adaptive decomposition methods is more effective than static decomposition alone. Value: Introducing HySQA provides the community with resources for evaluating the advancements in scholarly QA research.


  • Open Access

    Automating SPARQL Query Translations Between DBpedia and Wikidata

    by Malte Christian Bartels, Debayan Banerjee, Ricardo Usbeck

    Purpose: This paper investigates whether state-of-the-art Large Language Models (LLMs) can automatically translate SPARQL between popular Knowledge Graph (KG) schemas. We focus on translations between the DBpedia and Wikidata KG, and later on DBLP and OpenAlex KG. This study addresses a notable gap in KG interoperability research by evaluating LLM performance on SPARQL-to-SPARQL translation. Methodology: Two benchmarks are assembled, where the first aligns 100 DBpedia–Wikidata queries from QALD-9-Plus dataset; the second contains 100 DBLP queries aligned to OpenAlex, testing generalizability beyond encyclopaedic KGs. Three open LLMs: Llama-3-8B, DeepSeek-R1-Distill-Llama-70B, and Mistral-Large-Instruct-2407 are selected based on their sizes and architectures and tested with zero-shot, few-shot, and two chain-of-thought variants. Outputs were compared with gold-standard answers, and resulting errors were systematically categorized. Findings: We find that the performance varies markedly across models and prompting strategies, and that translations for Wikidata to DBpedia work far better than translations for DBpedia to Wikidata. The largest model, Mistral-Large-Instruct-2407, achieved the highest accuracy, reaching 86% on the Wikidata → DBpedia task using a Chain-of-Thought approach. This performance was replicated in the DBLP → OpenAlex generalization task, which achieved similar results with a few- shot setup, underscoring the critical role of in-context examples. Value: This study demonstrates a viable and scalable pathway toward KG interoperability by using LLMs with structured prompting and explicit schema-mapping tables to translate queries across heterogeneous KGs. The method’s strong performance when applied to general purpose KGs and specialized scholarly domain suggests its potential as a promising approach to reduce the manual effort required for cross-KG data integration and analysis.