Andrea Pasin
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Andrea Pasin has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Nicola Ferro
University of Padua, Padua, Italy
12 shared publications - Maurizio Ferrari Dacrema
Politecnico di Milano, Milano, Italy
8 shared publications - Paolo Cremonesi
Politecnico di Milano, Milano, Italy
8 shared publications - Marcos André Gonçalves
Federal University of Minas Gerais, Belo Horizonte, Brazil
5 shared publications - Washington Cunha
Universidade Estadual de Campinas
5 shared publications - Guglielmo Faggioli
University of Padua, Padua, Italy
2 shared publications
Latest Publications
- Open Access
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 3940-3951
Effective Re-Ranking with DIMEs using Few Noisy LLM-Generated Relevance Judgments
State-of-the-art Information Retrieval (IR) pipelines often rely on dense neural models to index and retrieve large document collections. After an initial retrieval stage, precision-oriented re-ranking approaches can further refine the ranked list. However, re-ranking quality strongly depends on the availability of reliable relevance signals. Recent work has explored the use of Large Language Models (LLMs) to automatically generate relevance judgments that can serve as such signals. However, achieving strong alignment with human gold labels generally requires either very large and complex LLMs or extensive human supervision. In this work, we investigate whether relatively small LLMs, despite producing limited and often noisy relevance assessments, can still be leveraged to improve the ranking of documents retrieved by dense bi-encoder models. Specifically, we introduce new approaches based on the recently proposed Dimension IMportance Estimators (DIMEs), incorporating LLM-generated relevance judgments into the re-ranking process. Our study assumes a practical setting: we consider access only to relatively small LLMs and to very small sets of relevance judgments generated for the top-retrieved documents of each query by dense retrieval models, and we investigate how to leverage these sparse, often noisy signals to refine the ranking of the entire retrieved set. Our method leads to substantial improvements in document ranking, boosting nDCG@10 and AP by up to 9% and 15%, respectively, across different datasets, LLMs, and bi-encoder backbone retrieval models. These results show that even a few noisy relevance judgments from small LLMs can provide a powerful signal to improve the effectiveness of IR systems.
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 3940-3951
Open AccessEffective Re-Ranking with DIMEs using Few Noisy LLM-Generated Relevance Judgments
State-of-the-art Information Retrieval (IR) pipelines often rely on dense neural models to index and retrieve large document collections. After an initial retrieval stage, precision-oriented re-ranking approaches can further refine the ranked list. However, re-ranking quality strongly depends on the availability of reliable relevance signals. Recent work has explored the use of Large Language Models (LLMs) to automatically generate relevance judgments that can serve as such signals. However, achieving strong alignment with human gold labels generally requires either very large and complex LLMs or extensive human supervision. In this work, we investigate whether relatively small LLMs, despite producing limited and often noisy relevance assessments, can still be leveraged to improve the ranking of documents retrieved by dense bi-encoder models. Specifically, we introduce new approaches based on the recently proposed Dimension IMportance Estimators (DIMEs), incorporating LLM-generated relevance judgments into the re-ranking process. Our study assumes a practical setting: we consider access only to relatively small LLMs and to very small sets of relevance judgments generated for the top-retrieved documents of each query by dense retrieval models, and we investigate how to leverage these sparse, often noisy signals to refine the ranking of the entire retrieved set. Our method leads to substantial improvements in document ranking, boosting nDCG@10 and AP by up to 9% and 15%, respectively, across different datasets, LLMs, and bi-encoder backbone retrieval models. These results show that even a few noisy relevance judgments from small LLMs can provide a powerful signal to improve the effectiveness of IR systems.
- 21 September 2026
- Published by Springer Nature
- p. 598-624
Overview of QuantumCLEF 2026: The Third Quantum Computing Challenge for Information Retrieval and Recommender Systems at CLEF
- 21 September 2026
- Published by Springer Nature
- p. 598-624
Overview of QuantumCLEF 2026: The Third Quantum Computing Challenge for Information Retrieval and Recommender Systems at CLEF
- 25 March 2026
- Published by Springer Nature
- p. 466-480
When Reducing Representations Improves Performance
- 25 March 2026
- Published by Springer Nature
- p. 466-480
When Reducing Representations Improves Performance
- 24 March 2026
- Published by Springer Nature
- p. 306-314
QuantumCLEF 2026 The Third Edition of the Quantum Computing Lab at CLEF
- 24 March 2026
- Published by Springer Nature
- p. 306-314
QuantumCLEF 2026 The Third Edition of the Quantum Computing Lab at CLEF
- Open Access
- 10 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 6801-6804
Investigating the Usage and Evaluation of Quantum Computing Technologies for Information Access
- 10 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 6801-6804
Open AccessInvestigating the Usage and Evaluation of Quantum Computing Technologies for Information Access
- 3 September 2025
- Published by Springer Nature
- p. 412-435
Overview of QuantumCLEF 2025: The Second Quantum Computing Challenge for Information Retrieval and Recommender Systems at CLEF
- 3 September 2025
- Published by Springer Nature
- p. 412-435
Overview of QuantumCLEF 2025: The Second Quantum Computing Challenge for Information Retrieval and Recommender Systems at CLEF
- Open Access
- 13 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 3584-3594
KIMERA: From Evaluation-as-a-Service to Evaluation-in-the-Cloud
- 13 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 3584-3594
Open AccessKIMERA: From Evaluation-as-a-Service to Evaluation-in-the-Cloud
- 3 April 2025
- Published by Springer Nature
- p. 450-458
QuantumCLEF 2025 - The Second Edition of the Quantum Computing Lab at CLEF
- 3 April 2025
- Published by Springer Nature
- p. 450-458
QuantumCLEF 2025 - The Second Edition of the Quantum Computing Lab at CLEF
- 19 September 2024
- Published by Springer Nature
- p. 260-282
Overview of QuantumCLEF 2024: The Quantum Computing Challenge for Information Retrieval and Recommender Systems at CLEF
- 19 September 2024
- Published by Springer Nature
- p. 260-282
Overview of QuantumCLEF 2024: The Quantum Computing Challenge for Information Retrieval and Recommender Systems at CLEF
- Open Access
- 2 August 2024
- Published by Association for Computing Machinery (ACM)
- p. 205-214
A Quantum Annealing Instance Selection Approach for Efficient and Effective Transformer Fine-Tuning
Deep Learning approaches have become pervasive in recent years due to their ability to solve complex tasks. However, these models need huge datasets for proper training and good generalization. This translates into high training and fine-tuning time, even several days for the most complex models and large datasets. In this work, we present a novel quantum Instance Selection (IS) approach that allows to significantly reduce the size of the training datasets (by up to 28%) while maintaining the model's effectiveness, thus promoting (training) speedups and scalability. Our solution is innovative in the sense that it exploits a different computing paradigm - Quantum Annealing (QA) - a specific Quantum Computing paradigm that can be used to tackle optimization problems. To the best of our knowledge, there have been no prior attempts to tackle the IS problem using QA. Furthermore, we propose a new Quadratic Unconstrained Binary Optimization formulation specific for the IS problem, which is a contribution in itself. Through an extensive set of experiments with several Text Classification benchmarks, we empirically demonstrate our quantum solution's feasibility and competitiveness with the current state-of-the-art IS solutions.
- 2 August 2024
- Published by Association for Computing Machinery (ACM)
- p. 205-214
Open AccessA Quantum Annealing Instance Selection Approach for Efficient and Effective Transformer Fine-Tuning
Deep Learning approaches have become pervasive in recent years due to their ability to solve complex tasks. However, these models need huge datasets for proper training and good generalization. This translates into high training and fine-tuning time, even several days for the most complex models and large datasets. In this work, we present a novel quantum Instance Selection (IS) approach that allows to significantly reduce the size of the training datasets (by up to 28%) while maintaining the model's effectiveness, thus promoting (training) speedups and scalability. Our solution is innovative in the sense that it exploits a different computing paradigm - Quantum Annealing (QA) - a specific Quantum Computing paradigm that can be used to tackle optimization problems. To the best of our knowledge, there have been no prior attempts to tackle the IS problem using QA. Furthermore, we propose a new Quadratic Unconstrained Binary Optimization formulation specific for the IS problem, which is a contribution in itself. Through an extensive set of experiments with several Text Classification benchmarks, we empirically demonstrate our quantum solution's feasibility and competitiveness with the current state-of-the-art IS solutions.