Pranav Kasela
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Pranav Kasela has a total of 21 co-authors. Here are the top co-authors by number of shared publications:
- Gabriella Pasi
University of Milano-Bicocca, DISCo
15 shared publications - Georgios Peikos
University of Milano-Bicocca, Milan, Italy
6 shared publications - Raffaele Perego
ISTI-CNR, Pisa, Italy
6 shared publications - Marco Braga
University of Milano-Bicocca, Milan, Italy
5 shared publications - Effrosyni Sokli
University of Milano-Bicocca Milan Italy
4 shared publications - Alessandro Raganato
Department of Informatics, Systems and Communication - DISCo, University of Milano-Bicocca, Milan, Italy
2 shared publications
Latest Publications
- Open Access
- 11 June 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Information Systems
- Vol. 44 (5) , 1-29
Toward Exploring Mixed-Initiative Conversation Generation Based on Community Question Answering
Conversational search addresses users’ information needs through multi-turn and context-aware interactions. Given that user queries are often ambiguous, the use of clarifying questions can effectively reduce uncertainty and enable a mixed-initiative conversational system. However, current datasets for clarifying questions remain limited in the following three aspects: (1) underrepresented multi-turn conversational data, (2) limited diversity, and (3) heavily reliance on crowdsourcing, thereby suffering from limitations such as high annotation cost. To address these issues, we propose a large language model (LLM)-based three-stage framework that relies on an existing community question answering dataset. It encompasses: (1) extracting essential information from the initial user query with the relevant contextual information, (2) generating clarifying questions paired with corresponding answers, and (3) refining conversations to ensure coherence and a natural conversational flow. We assess our multi-stage method against a baseline that directly prompts LLMs to generate conversations in a single-step process, evaluating on an answer retrieval task using recall, precision, normalized discounted cumulative gain and mean average precision. Results show that our three-stage generation approach consistently outperforms the baseline particularly in recall, while also achieving competitive results across other metrics. Human and automatic evaluations further indicate the high quality of generated conversations and fine-tuning on them improves retrieval performance, highlighting the pipeline’s potential.
- 11 June 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Information Systems
- Vol. 44 (5) , 1-29
Open AccessToward Exploring Mixed-Initiative Conversation Generation Based on Community Question Answering
Conversational search addresses users’ information needs through multi-turn and context-aware interactions. Given that user queries are often ambiguous, the use of clarifying questions can effectively reduce uncertainty and enable a mixed-initiative conversational system. However, current datasets for clarifying questions remain limited in the following three aspects: (1) underrepresented multi-turn conversational data, (2) limited diversity, and (3) heavily reliance on crowdsourcing, thereby suffering from limitations such as high annotation cost. To address these issues, we propose a large language model (LLM)-based three-stage framework that relies on an existing community question answering dataset. It encompasses: (1) extracting essential information from the initial user query with the relevant contextual information, (2) generating clarifying questions paired with corresponding answers, and (3) refining conversations to ensure coherence and a natural conversational flow. We assess our multi-stage method against a baseline that directly prompts LLMs to generate conversations in a single-step process, evaluating on an answer retrieval task using recall, precision, normalized discounted cumulative gain and mean average precision. Results show that our three-stage generation approach consistently outperforms the baseline particularly in recall, while also achieving competitive results across other metrics. Human and automatic evaluations further indicate the high quality of generated conversations and fine-tuning on them improves retrieval performance, highlighting the pipeline’s potential.
- 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
DIETA: A Decoder-only transformer-based model for Italian-English machine TrAnslation
In this paper, we present DIETA, a small, decoder-only Transformer model with 0.5 billion parameters, specifically designed and trained for Italian-English machine translation. We collect and curate a large parallel corpus consisting of approximately 207 million Italian-English sentence pairs across diverse domains, including parliamentary proceedings, legal texts, web-crawled content, subtitles, news, literature and 352 million back-translated data using pretrained models. Additionally, we create and release a new small-scale evaluation set, consisting of 450 sentences, based on 2025 WikiNews articles, enabling assessment of translation quality on contemporary text. Comprehensive evaluations show that DIETA achieves competitive performance on multiple Italian-English benchmarks, consistently ranking in the second quartile of a 32-system leaderboard and outperforming most other sub-3B models on four out of five test suites. The training script, trained models, curated corpus, and newly introduced evaluation set are made publicly available, facilitating further research and development in specialized Italian-English machine translation. https://github.com/pkasela/DIETA-Machine-Translation
Open AccessDIETA: A Decoder-only transformer-based model for Italian-English machine TrAnslation
In this paper, we present DIETA, a small, decoder-only Transformer model with 0.5 billion parameters, specifically designed and trained for Italian-English machine translation. We collect and curate a large parallel corpus consisting of approximately 207 million Italian-English sentence pairs across diverse domains, including parliamentary proceedings, legal texts, web-crawled content, subtitles, news, literature and 352 million back-translated data using pretrained models. Additionally, we create and release a new small-scale evaluation set, consisting of 450 sentences, based on 2025 WikiNews articles, enabling assessment of translation quality on contemporary text. Comprehensive evaluations show that DIETA achieves competitive performance on multiple Italian-English benchmarks, consistently ranking in the second quartile of a 32-system leaderboard and outperforming most other sub-3B models on four out of five test suites. The training script, trained models, curated corpus, and newly introduced evaluation set are made publicly available, facilitating further research and development in specialized Italian-English machine translation. https://github.com/pkasela/DIETA-Machine-Translation
- Open Access
Mixture of Experts Approaches in Dense Retrieval Tasks
Dense Retrieval Models (DRMs) are a prominent development in Information Retrieval (IR). A key challenge with these neural Transformer-based models is that they often struggle to generalize beyond the specific tasks and domains they were trained on. To address this challenge, prior research in IR incorporated the Mixture-of-Experts (MoE) framework within each Transformer layer of a DRM, which, though effective, substantially increased the number of additional parameters. In this paper, we propose a more efficient design, which introduces a single MoE block (SB-MoE) after the final Transformer layer. To assess the retrieval effectiveness of SB-MoE, we perform an empirical evaluation across three IR tasks. Our experiments involve two evaluation setups, aiming to assess both in-domain effectiveness and the model's zero-shot generalizability. In the first setup, we fine-tune SB-MoE with four different underlying DRMs on seven IR benchmarks and evaluate them on their respective test sets. In the second setup, we fine-tune SB-MoE on MSMARCO and perform zero-shot evaluation on thirteen BEIR datasets. Additionally, we perform further experiments to analyze the model's dependency on its hyperparameters (i.e., the number of employed and activated experts) and investigate how this variation affects SB-MoE's performance. The obtained results show that SB-MoE is particularly effective for DRMs with lightweight base models, such as TinyBERT and BERT-Small, consistently exceeding standard model fine-tuning across benchmarks. For DRMs with more parameters, such as BERT-Base and Contriever, our model requires a larger number of training samples to achieve improved retrieval performance. Our code is available online at: https://github.com/FaySokli/SB-MoE.
Open AccessMixture of Experts Approaches in Dense Retrieval Tasks
Dense Retrieval Models (DRMs) are a prominent development in Information Retrieval (IR). A key challenge with these neural Transformer-based models is that they often struggle to generalize beyond the specific tasks and domains they were trained on. To address this challenge, prior research in IR incorporated the Mixture-of-Experts (MoE) framework within each Transformer layer of a DRM, which, though effective, substantially increased the number of additional parameters. In this paper, we propose a more efficient design, which introduces a single MoE block (SB-MoE) after the final Transformer layer. To assess the retrieval effectiveness of SB-MoE, we perform an empirical evaluation across three IR tasks. Our experiments involve two evaluation setups, aiming to assess both in-domain effectiveness and the model's zero-shot generalizability. In the first setup, we fine-tune SB-MoE with four different underlying DRMs on seven IR benchmarks and evaluate them on their respective test sets. In the second setup, we fine-tune SB-MoE on MSMARCO and perform zero-shot evaluation on thirteen BEIR datasets. Additionally, we perform further experiments to analyze the model's dependency on its hyperparameters (i.e., the number of employed and activated experts) and investigate how this variation affects SB-MoE's performance. The obtained results show that SB-MoE is particularly effective for DRMs with lightweight base models, such as TinyBERT and BERT-Small, consistently exceeding standard model fine-tuning across benchmarks. For DRMs with more parameters, such as BERT-Base and Contriever, our model requires a larger number of training samples to achieve improved retrieval performance. Our code is available online at: https://github.com/FaySokli/SB-MoE.
- Open Access
- 13 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 2738-2743
Investigating Task Arithmetic for Zero-Shot Information Retrieval
- 13 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 2738-2743
Open AccessInvestigating Task Arithmetic for Zero-Shot Information Retrieval
- Open Access
- 3 June 2025
- Published by Elsevier in Information Systems
- Vol. 134
PARK: Personalized academic retrieval with knowledge-graphs
- 3 June 2025
- Published by Elsevier in Information Systems
- Vol. 134
Open AccessPARK: Personalized academic retrieval with knowledge-graphs
- Open Access
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 27071-27084
Leveraging Cognitive Complexity of Texts for Contextualization in Dense Retrieval
Effrosyni Sokli, Georgios Peikos, Pranav Kasela, Gabriella Pasi. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 27071-27084
Open AccessLeveraging Cognitive Complexity of Texts for Contextualization in Dense Retrieval
Effrosyni Sokli, Georgios Peikos, Pranav Kasela, Gabriella Pasi. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.
- Open Access
Investigating Mixture of Experts in Dense Retrieval
While Dense Retrieval Models (DRMs) have advanced Information Retrieval (IR), one limitation of these neural models is their narrow generalizability and robustness. To cope with this issue, one can leverage the Mixture-of-Experts (MoE) architecture. While previous IR studies have incorporated MoE architectures within the Transformer layers of DRMs, our work investigates an architecture that integrates a single MoE block (SB-MoE) after the output of the final Transformer layer. Our empirical evaluation investigates how SB-MoE compares, in terms of retrieval effectiveness, to standard fine-tuning. In detail, we fine-tune three DRMs (TinyBERT, BERT, and Contriever) across four benchmark collections with and without adding the MoE block. Moreover, since MoE showcases performance variations with respect to its parameters (i.e., the number of experts), we conduct additional experiments to investigate this aspect further. The findings show the effectiveness of SB-MoE especially for DRMs with a low number of parameters (i.e., TinyBERT), as it consistently outperforms the fine-tuned underlying model on all four benchmarks. For DRMs with a higher number of parameters (i.e., BERT and Contriever), SB-MoE requires larger numbers of training samples to yield better retrieval performance.
Open AccessInvestigating Mixture of Experts in Dense Retrieval
While Dense Retrieval Models (DRMs) have advanced Information Retrieval (IR), one limitation of these neural models is their narrow generalizability and robustness. To cope with this issue, one can leverage the Mixture-of-Experts (MoE) architecture. While previous IR studies have incorporated MoE architectures within the Transformer layers of DRMs, our work investigates an architecture that integrates a single MoE block (SB-MoE) after the output of the final Transformer layer. Our empirical evaluation investigates how SB-MoE compares, in terms of retrieval effectiveness, to standard fine-tuning. In detail, we fine-tune three DRMs (TinyBERT, BERT, and Contriever) across four benchmark collections with and without adding the MoE block. Moreover, since MoE showcases performance variations with respect to its parameters (i.e., the number of experts), we conduct additional experiments to investigate this aspect further. The findings show the effectiveness of SB-MoE especially for DRMs with a low number of parameters (i.e., TinyBERT), as it consistently outperforms the fine-tuned underlying model on all four benchmarks. For DRMs with a higher number of parameters (i.e., BERT and Contriever), SB-MoE requires larger numbers of training samples to yield better retrieval performance.
- Open Access
- 12 December 2024
- Published by Association for Computing Machinery (ACM)
- p. 11-13
Overview of the PIR Track at FIRE 2024: Evaluation of Personalised Information Retrieval
- 12 December 2024
- Published by Association for Computing Machinery (ACM)
- p. 11-13
Open AccessOverview of the PIR Track at FIRE 2024: Evaluation of Personalised Information Retrieval
- Open Access
Leveraging Large Language Models for Medical Information Extraction and Query Generation
This paper introduces a system that integrates large language models (LLMs) into the clinical trial retrieval process, enhancing the effectiveness of matching patients with eligible trials while maintaining information privacy and allowing expert oversight. We evaluate six LLMs for query generation, focusing on open-source and relatively small models that require minimal computational resources. Our evaluation includes two closed-source and four open-source models, with one specifically trained in the medical field and five general-purpose models. We compare the retrieval effectiveness achieved by LLM-generated queries against those created by medical experts and state-of-the-art methods from the literature. Our findings indicate that the evaluated models reach retrieval effectiveness on par with or greater than expert-created queries. The LLMs consistently outperform standard baselines and other approaches in the literature. The best performing LLMs exhibit fast response times, ranging from 1.7 to 8 seconds, and generate a manageable number of query terms (15-63 on average), making them suitable for practical implementation. Our overall findings suggest that leveraging small, open-source LLMs for clinical trials retrieval can balance performance, computational efficiency, and real-world applicability in medical settings.
Open AccessLeveraging Large Language Models for Medical Information Extraction and Query Generation
This paper introduces a system that integrates large language models (LLMs) into the clinical trial retrieval process, enhancing the effectiveness of matching patients with eligible trials while maintaining information privacy and allowing expert oversight. We evaluate six LLMs for query generation, focusing on open-source and relatively small models that require minimal computational resources. Our evaluation includes two closed-source and four open-source models, with one specifically trained in the medical field and five general-purpose models. We compare the retrieval effectiveness achieved by LLM-generated queries against those created by medical experts and state-of-the-art methods from the literature. Our findings indicate that the evaluated models reach retrieval effectiveness on par with or greater than expert-created queries. The LLMs consistently outperform standard baselines and other approaches in the literature. The best performing LLMs exhibit fast response times, ranging from 1.7 to 8 seconds, and generate a manageable number of query terms (15-63 on average), making them suitable for practical implementation. Our overall findings suggest that leveraging small, open-source LLMs for clinical trials retrieval can balance performance, computational efficiency, and real-world applicability in medical settings.