Manolis Koubarakis
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Manolis Koubarakis has a total of 139 co-authors. Here are the top co-authors by number of shared publications:
- George Papadakis
National and Kapodistrian University of Athens, Athens, Greece
12 shared publications - Eleni Tsalapati
Athens Technology Center
5 shared publications - Alexandros Zeakis
National and Kapodistrian University of Athens
4 shared publications - Despina-Athanasia Pantazi
National and Kapodistrian University of Athens
4 shared publications - Dimitrios Skoutas
Athena Research Center, Athens, Greece
4 shared publications - George Stamoulis
National and Kapodistrian University of Athens
4 shared publications
Latest Publications
- Open Access
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 2053-2063
SPER: Accelerating Progressive Entity Resolution via Stochastic Bipartite Maximization
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 2053-2063
Open AccessSPER: Accelerating Progressive Entity Resolution via Stochastic Bipartite Maximization
- 18 October 2026
- Published by Springer Nature
- p. 3-17
Cardinal Direction Reasoning Using Large Reasoning Models
- 18 October 2026
- Published by Springer Nature
- p. 3-17
Cardinal Direction Reasoning Using Large Reasoning Models
- 1 September 2026
- Published by Springer Nature
- p. 108-130
Evaluating Large Language Models’ Ability to Reason About Anatomical Spatial Relations
- 1 September 2026
- Published by Springer Nature
- p. 108-130
Evaluating Large Language Models’ Ability to Reason About Anatomical Spatial Relations
- Open Access
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 2285-2296
PYTHIA: Universal Question Answering over Knowledge Graphs
Knowledge graph question answering (KGQA) focuses on answering questions with data retrieved from knowledge graphs (KGs). Although Large Language Models (LLMs) have enabled the development of innovative KGQA systems, serious challenges remain. Approaches that utilize supervised finetuning are accurate and responsive, but also require large training datasets that provide good coverage of both the target knowledge graph and expected user questions. Likewise, integrating KG-specific optimizations improves accuracy and responsiveness but limits versatility and is susceptible to updates to the KG's ontology. LLMs have facilitated the development of training-free and KG-agnostic solutions that utilize reasoning and real-time decision making to explore the target KG, but the semi-structured nature of KGs makes this a complex and unpredictable task, leading to performance degradation and longer response times. In this paper we present PYTHIA, a training-free, plug-and-play solution for KGQA over any RDF KG. At its core, PYTHIA consists of an LLM agent guided by a relation-centric conceptual model of the KGQA task which is acted upon through a suite of tools for entity linking, graph exploration and query execution. The agent is responsible for interpreting user intent, orchestrating tool calls, and evaluating tool output, while the tools themselves present simple interfaces that abstract complex processes, reducing cognitive load on the agent. To assess its viability, we perform a comprehensive evaluation of PYTHIA and prior systems across four knowledge graphs and six datasets. The results show PYTHIA achieving a median performance improvement of 15.31% while improving cost and time efficiency at the performance frontier.
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 2285-2296
Open AccessPYTHIA: Universal Question Answering over Knowledge Graphs
Knowledge graph question answering (KGQA) focuses on answering questions with data retrieved from knowledge graphs (KGs). Although Large Language Models (LLMs) have enabled the development of innovative KGQA systems, serious challenges remain. Approaches that utilize supervised finetuning are accurate and responsive, but also require large training datasets that provide good coverage of both the target knowledge graph and expected user questions. Likewise, integrating KG-specific optimizations improves accuracy and responsiveness but limits versatility and is susceptible to updates to the KG's ontology. LLMs have facilitated the development of training-free and KG-agnostic solutions that utilize reasoning and real-time decision making to explore the target KG, but the semi-structured nature of KGs makes this a complex and unpredictable task, leading to performance degradation and longer response times. In this paper we present PYTHIA, a training-free, plug-and-play solution for KGQA over any RDF KG. At its core, PYTHIA consists of an LLM agent guided by a relation-centric conceptual model of the KGQA task which is acted upon through a suite of tools for entity linking, graph exploration and query execution. The agent is responsible for interpreting user intent, orchestrating tool calls, and evaluating tool output, while the tools themselves present simple interfaces that abstract complex processes, reducing cognitive load on the agent. To assess its viability, we perform a comprehensive evaluation of PYTHIA and prior systems across four knowledge graphs and six datasets. The results show PYTHIA achieving a median performance improvement of 15.31% while improving cost and time efficiency at the performance frontier.
- Open Access
DistillER: Knowledge Distillation in Entity Resolution with Large Language Models
Recent advances in Entity Resolution (ER) have leveraged Large Language Models (LLMs), achieving strong performance but at the cost of substantial computational resources or high financial overhead. Existing LLM-based ER approaches operate either in unsupervised settings and rely on very large and costly models, or in supervised settings and require ground-truth annotations, leaving a critical gap between time efficiency and effectiveness. To make LLM-powered ER more practical, we investigate Knowledge Distillation (KD) as a means to transfer knowledge from large, effective models (Teachers) to smaller, more efficient models (Students) without requiring gold labels. We introduce DistillER, the first framework that systematically bridges this gap across three dimensions: (i) Data Selection, where we study strategies for identifying informative subsets of data; (ii) Knowledge Elicitation, where we compare single- and multi-teacher settings across LLMs and smaller language models (SLMs); and (iii) Distillation Algorithms, where we evaluate supervised fine-tuning and reinforcement learning approaches. Our experiments reveal that supervised fine-tuning of Students on noisy labels generated by LLM Teachers consistently outperforms alternative KD strategies, while also enabling high-quality explanation generation. Finally, we benchmark DistillER against established supervised and unsupervised ER methods based on LLMs and SLMs, demonstrating significant improvements in both effectiveness and efficiency.
Open AccessDistillER: Knowledge Distillation in Entity Resolution with Large Language Models
Recent advances in Entity Resolution (ER) have leveraged Large Language Models (LLMs), achieving strong performance but at the cost of substantial computational resources or high financial overhead. Existing LLM-based ER approaches operate either in unsupervised settings and rely on very large and costly models, or in supervised settings and require ground-truth annotations, leaving a critical gap between time efficiency and effectiveness. To make LLM-powered ER more practical, we investigate Knowledge Distillation (KD) as a means to transfer knowledge from large, effective models (Teachers) to smaller, more efficient models (Students) without requiring gold labels. We introduce DistillER, the first framework that systematically bridges this gap across three dimensions: (i) Data Selection, where we study strategies for identifying informative subsets of data; (ii) Knowledge Elicitation, where we compare single- and multi-teacher settings across LLMs and smaller language models (SLMs); and (iii) Distillation Algorithms, where we evaluate supervised fine-tuning and reinforcement learning approaches. Our experiments reveal that supervised fine-tuning of Students on noisy labels generated by LLM Teachers consistently outperforms alternative KD strategies, while also enabling high-quality explanation generation. Finally, we benchmark DistillER against established supervised and unsupervised ER methods based on LLMs and SLMs, demonstrating significant improvements in both effectiveness and efficiency.
- Open Access
- 3 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 81-91
Can Large Reasoning Models Reason about Spatial Relations?
- 3 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 81-91
Open AccessCan Large Reasoning Models Reason about Spatial Relations?
- Open Access
Harnessing Collective Intelligence of LLMs for Robust Biomedical QA: A Multi-Model Approach
Biomedical text mining and question-answering are essential yet highly demanding tasks, particularly in the face of the exponential growth of biomedical literature. In this work, we present our participation in the 13th edition of the BioASQ challenge, which involves biomedical semantic question-answering for Task 13b and biomedical question-answering for developing topics for the Synergy task. We deploy a selection of open-source large language models (LLMs) as retrieval-augmented generators to answer biomedical questions. Various models are used to process the questions. A majority voting system combines their output to determine the final answer for Yes/No questions, while for list and factoid type questions, the union of their answers in used. We evaluated 13 state-of-the-art open source LLMs, exploring all possible model combinations to contribute to the final answer, resulting in tailored LLM pipelines for each question type. Our findings provide valuable insight into which combinations of LLMs consistently produce superior results for specific question types. In the four rounds of the 2025 BioASQ challenge, our system achieved notable results: in the Synergy task, we secured 1st place for ideal answers and 2nd place for exact answers in round 2, as well as two shared 1st places for exact answers in round 3 and 4.
Open AccessHarnessing Collective Intelligence of LLMs for Robust Biomedical QA: A Multi-Model Approach
Biomedical text mining and question-answering are essential yet highly demanding tasks, particularly in the face of the exponential growth of biomedical literature. In this work, we present our participation in the 13th edition of the BioASQ challenge, which involves biomedical semantic question-answering for Task 13b and biomedical question-answering for developing topics for the Synergy task. We deploy a selection of open-source large language models (LLMs) as retrieval-augmented generators to answer biomedical questions. Various models are used to process the questions. A majority voting system combines their output to determine the final answer for Yes/No questions, while for list and factoid type questions, the union of their answers in used. We evaluated 13 state-of-the-art open source LLMs, exploring all possible model combinations to contribute to the final answer, resulting in tailored LLM pipelines for each question type. Our findings provide valuable insight into which combinations of LLMs consistently produce superior results for specific question types. In the four rounds of the 2025 BioASQ challenge, our system achieved notable results: in the Synergy task, we secured 1st place for ideal answers and 2nd place for exact answers in round 2, as well as two shared 1st places for exact answers in round 3 and 4.
- 1 June 2025
- Published by Springer Nature
- p. 301-320
AvengER: Ensembling and Fine-Tuning LLMs for SELECT Prompts in Entity Resolution
- 1 June 2025
- Published by Springer Nature
- p. 301-320
AvengER: Ensembling and Fine-Tuning LLMs for SELECT Prompts in Entity Resolution
- 28 February 2025
- Published by Springer Nature
- p. 233-242
Developing Geospatial Web Applications Using Question Answering Engines, Knowledge Graphs and Linked Data Tools
- 28 February 2025
- Published by Springer Nature
- p. 233-242
Developing Geospatial Web Applications Using Question Answering Engines, Knowledge Graphs and Linked Data Tools
- 28 February 2025
- Published by Springer Nature
- p. 243-248
A Visual Query Builder for DBpedia