Raffaele Perego
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Raffaele Perego has a total of 177 co-authors. Here are the top co-authors by number of shared publications:
- Salvatore Orlando
Ca' Foscari University of Venice, Venice, Italy
57 shared publications - Claudio Lucchese
Ca' Foscari University of Venice, Venice, Italy
39 shared publications - Fabrizio Silvestri
Sapienza University of Rome, Rome, Italy
34 shared publications - Franco Maria Nardini
ISTI-CNR, Pisa, Italy
34 shared publications - Nicola Tonellotto
University of Pisa, Pisa, Italy
27 shared publications - Chiara Renso
ISTI-CNR, Pisa, Italy
13 shared publications
Latest Publications
- Open Access
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 139-150
Embedding Surgery: Localized Updates for Adaptive Ranking Correction in Dense Retrieval
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 139-150
Open AccessEmbedding Surgery: Localized Updates for Adaptive Ranking Correction in Dense Retrieval
- Open Access
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 6844-6849
Conformal Prediction for Statistically Reliable LLM-as-a-Judge in Recommender Systems
LLM-as-a-judge has emerged as a promising strategy for evaluating recommender systems. Yet, treating simulated ratings as real feedback can make unreliable evaluation appear reliable. This risk is especially consequential in sensitive domains such as nutrition and health. In this paper, we treat the LLM-as-a-judge paradigm as a calibrated relevance simulation problem: an LLM-based simulator predicts human preferences from user and item representations, and conformal prediction converts them into uncertainty intervals. To account for the nature of recommendation, we introduce stratified conformal calibration by user rating variance. Experiments under three LLMs and seven conformal prediction methods show that point estimates of preferences hide failures on low-rating items, while conformal interval width is driven by user-level heterogeneity. Source code and data: https://github.com/maddalena-amendola/conformal_prediction_recsys.
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 6844-6849
Open AccessConformal Prediction for Statistically Reliable LLM-as-a-Judge in Recommender Systems
LLM-as-a-judge has emerged as a promising strategy for evaluating recommender systems. Yet, treating simulated ratings as real feedback can make unreliable evaluation appear reliable. This risk is especially consequential in sensitive domains such as nutrition and health. In this paper, we treat the LLM-as-a-judge paradigm as a calibrated relevance simulation problem: an LLM-based simulator predicts human preferences from user and item representations, and conformal prediction converts them into uncertainty intervals. To account for the nature of recommendation, we introduce stratified conformal calibration by user rating variance. Experiments under three LLMs and seven conformal prediction methods show that point estimates of preferences hide failures on low-rating items, while conformal interval width is driven by user-level heterogeneity. Source code and data: https://github.com/maddalena-amendola/conformal_prediction_recsys.
- 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.
- Open Access
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 7628-7633
Simplify, Then Retrieve: Evaluating Meaning Preservation through Search Behavior
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 7628-7633
Open AccessSimplify, Then Retrieve: Evaluating Meaning Preservation through Search Behavior
- Open Access
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 6821-6826
Multi-Aspect Joint Retrieval for E-Commerce: Bridging Product Catalogs and Customer Reviews
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 6821-6826
Open AccessMulti-Aspect Joint Retrieval for E-Commerce: Bridging Product Catalogs and Customer Reviews
- 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
- Open Access
- 25 March 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Information Systems
- Vol. 44 (3) , 1-37
Leveraging Topic Specificity and Social Relationships for Expert Finding in Community Question Answering Platforms
Online Community Question Answering (CQA) platforms have become indispensable tools for users seeking expert solutions to their technical queries. The effectiveness of these platforms relies on their ability to identify and direct questions to the most knowledgeable users within the community, a process known as Expert Finding (EF). EF accuracy is crucial for increasing user engagement and the reliability of the provided answers. We present TUEF, a Topic-Oriented User-Interaction Model for EF , which aims to fully and transparently leverage the heterogeneous information available within online CQA platforms. TUEF integrates content and social data by constructing a multi-layer graph that maps user relationships based on their answering patterns on specific topics. By combining these sources of information, TUEF identifies the most relevant users for any given question and ranks them using learning-to-rank techniques. Our findings indicate that TUEF’s topic-oriented model significantly enhances performance, particularly in large communities discussing well-defined topics. Additionally, we show that the interpretable learning-to-rank algorithm integrated into TUEF offers transparency and explainability with minimal performance tradeoffs. The exhaustive experiments conducted across six CQA communities show that TUEF outperforms all competitors, achieving a minimum performance boost of 42.42% in P@1, 32.73% in NDCG@3, 21.76% in R@5, and 29.81% in MRR.
- 25 March 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Information Systems
- Vol. 44 (3) , 1-37
Open AccessLeveraging Topic Specificity and Social Relationships for Expert Finding in Community Question Answering Platforms
Online Community Question Answering (CQA) platforms have become indispensable tools for users seeking expert solutions to their technical queries. The effectiveness of these platforms relies on their ability to identify and direct questions to the most knowledgeable users within the community, a process known as Expert Finding (EF). EF accuracy is crucial for increasing user engagement and the reliability of the provided answers. We present TUEF, a Topic-Oriented User-Interaction Model for EF , which aims to fully and transparently leverage the heterogeneous information available within online CQA platforms. TUEF integrates content and social data by constructing a multi-layer graph that maps user relationships based on their answering patterns on specific topics. By combining these sources of information, TUEF identifies the most relevant users for any given question and ranks them using learning-to-rank techniques. Our findings indicate that TUEF’s topic-oriented model significantly enhances performance, particularly in large communities discussing well-defined topics. Additionally, we show that the interpretable learning-to-rank algorithm integrated into TUEF offers transparency and explainability with minimal performance tradeoffs. The exhaustive experiments conducted across six CQA communities show that TUEF outperforms all competitors, achieving a minimum performance boost of 42.42% in P@1, 32.73% in NDCG@3, 21.76% in R@5, and 29.81% in MRR.
- Open Access
DRAMA: Domain Retrieval using Adaptive Module Allocation
Neural models are increasingly used in Web-scale Information Retrieval (IR). However, relying on these models introduces substantial computational and energy requirements, leading to increasing attention toward their environmental cost and the sustainability of large-scale deployments. While neural IR models deliver high retrieval effectiveness, their scalability is constrained in multi-domain scenarios, where training and maintaining domain-specific models is inefficient and achieving robust cross-domain generalisation within a unified model remains difficult. This paper introduces DRAMA (Domain Retrieval using Adaptive Module Allocation), an energy- and parameter-efficient framework designed to reduce the environmental footprint of neural retrieval. DRAMA integrates domain-specific adapter modules with a dynamic gating mechanism that selects the most relevant domain knowledge for each query. New domains can be added efficiently through lightweight adapter training, avoiding full model retraining. We evaluate DRAMA on multiple Web retrieval benchmarks covering different domains. Our extensive evaluation shows that DRAMA achieves comparable effectiveness to domain-specific models while using only a fraction of their parameters and computational resources. These findings show that energy-aware model design can significantly improve scalability and sustainability in neural IR.
Open AccessDRAMA: Domain Retrieval using Adaptive Module Allocation
Neural models are increasingly used in Web-scale Information Retrieval (IR). However, relying on these models introduces substantial computational and energy requirements, leading to increasing attention toward their environmental cost and the sustainability of large-scale deployments. While neural IR models deliver high retrieval effectiveness, their scalability is constrained in multi-domain scenarios, where training and maintaining domain-specific models is inefficient and achieving robust cross-domain generalisation within a unified model remains difficult. This paper introduces DRAMA (Domain Retrieval using Adaptive Module Allocation), an energy- and parameter-efficient framework designed to reduce the environmental footprint of neural retrieval. DRAMA integrates domain-specific adapter modules with a dynamic gating mechanism that selects the most relevant domain knowledge for each query. New domains can be added efficiently through lightweight adapter training, avoiding full model retraining. We evaluate DRAMA on multiple Web retrieval benchmarks covering different domains. Our extensive evaluation shows that DRAMA achieves comparable effectiveness to domain-specific models while using only a fraction of their parameters and computational resources. These findings show that energy-aware model design can significantly improve scalability and sustainability in neural IR.
- Open Access
- 3 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 840-843
A Spatially-Grounded Conversational Planner for Personalized Urban Itineraries
- 3 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 840-843
Open AccessA Spatially-Grounded Conversational Planner for Personalized Urban Itineraries
- Open Access
Blending Learning to Rank and Dense Representations for Efficient and Effective Cascades
We investigate the exploitation of both lexical and neural relevance signals for ad-hoc passage retrieval. Our exploration involves a large-scale training dataset in which dense neural representations of MS-MARCO queries and passages are complemented and integrated with 253 hand-crafted lexical features extracted from the same corpus. Blending of the relevance signals from the two different groups of features is learned by a classical Learning-to-Rank (LTR) model based on a forest of decision trees. To evaluate our solution, we employ a pipelined architecture where a dense neural retriever serves as the first stage and performs a nearest-neighbor search over the neural representations of the documents. Our LTR model acts instead as the second stage that re-ranks the set of candidates retrieved by the first stage to enhance effectiveness. The results of reproducible experiments conducted with state-of-the-art dense retrievers on publicly available resources show that the proposed solution significantly enhances the end-to-end ranking performance while relatively minimally impacting efficiency. Specifically, we achieve a boost in nDCG@10 of up to 11% with an increase in average query latency of only 4.3%. This confirms the advantage of seamlessly combining two distinct families of signals that mutually contribute to retrieval effectiveness.
Open AccessBlending Learning to Rank and Dense Representations for Efficient and Effective Cascades
We investigate the exploitation of both lexical and neural relevance signals for ad-hoc passage retrieval. Our exploration involves a large-scale training dataset in which dense neural representations of MS-MARCO queries and passages are complemented and integrated with 253 hand-crafted lexical features extracted from the same corpus. Blending of the relevance signals from the two different groups of features is learned by a classical Learning-to-Rank (LTR) model based on a forest of decision trees. To evaluate our solution, we employ a pipelined architecture where a dense neural retriever serves as the first stage and performs a nearest-neighbor search over the neural representations of the documents. Our LTR model acts instead as the second stage that re-ranks the set of candidates retrieved by the first stage to enhance effectiveness. The results of reproducible experiments conducted with state-of-the-art dense retrievers on publicly available resources show that the proposed solution significantly enhances the end-to-end ranking performance while relatively minimally impacting efficiency. Specifically, we achieve a boost in nDCG@10 of up to 11% with an increase in average query latency of only 4.3%. This confirms the advantage of seamlessly combining two distinct families of signals that mutually contribute to retrieval effectiveness.