Typology
operator:
and / or
Language
operator:
and / or
Date
operator:
and / or
Rights
operator:
and / or
2024
Journal article
Open Access
Using large language models to create narrative events
Bartalesi Lenzi V., Lenzi E., De Martino C.
Narratives play a crucial role in human communication, serving as a means to convey experiences, perspectives, and meanings across various domains. They are particularly significant in scientific communities, where narratives are often utilized to explain complex phenomena and share knowledge. This article explores the possibility of integrating large language models (LLMs) into a workflow that, exploiting the Semantic Web technologies, transforms raw textual data gathered by scientific communities into narratives. In particular, we focus on using LLMs to automatically create narrative events, maintaining the reliability of the generated texts. The study provides a conceptual definition of narrative events and evaluates the performance of different smaller LLMs compared to the requirements we identified. A key aspect of the experiment is the emphasis on maintaining the integrity of the original narratives in the LLM outputs, as experts often review texts produced by scientific communities to ensure their accuracy and reliability. We first perform an evaluation on a corpus of five narratives and then on a larger dataset comprising 124 narratives. LLaMA 2 is identified as the most suitable model for generating narrative events that closely align with the input texts, demonstrating its ability to generate high-quality narrative events. Prompt engineering techniques are then employed to enhance the performance of the selected model, leading to further improvements in the quality of the generated texts.Source: PEERJ. COMPUTER SCIENCE., vol. 10
DOI: 10.7717/peerj-cs.2242
Project(s): Craeft
Metrics:
Bartalesi Lenzi V., Lenzi E., De Martino C.
Narratives play a crucial role in human communication, serving as a means to convey experiences, perspectives, and meanings across various domains. They are particularly significant in scientific communities, where narratives are often utilized to explain complex phenomena and share knowledge. This article explores the possibility of integrating large language models (LLMs) into a workflow that, exploiting the Semantic Web technologies, transforms raw textual data gathered by scientific communities into narratives. In particular, we focus on using LLMs to automatically create narrative events, maintaining the reliability of the generated texts. The study provides a conceptual definition of narrative events and evaluates the performance of different smaller LLMs compared to the requirements we identified. A key aspect of the experiment is the emphasis on maintaining the integrity of the original narratives in the LLM outputs, as experts often review texts produced by scientific communities to ensure their accuracy and reliability. We first perform an evaluation on a corpus of five narratives and then on a larger dataset comprising 124 narratives. LLaMA 2 is identified as the most suitable model for generating narrative events that closely align with the input texts, demonstrating its ability to generate high-quality narrative events. Prompt engineering techniques are then employed to enhance the performance of the selected model, leading to further improvements in the quality of the generated texts.Source: PEERJ. COMPUTER SCIENCE., vol. 10
DOI: 10.7717/peerj-cs.2242
Project(s): Craeft
Metrics:
See at:
PeerJ Computer Science 
| PeerJ Computer Science | IRIS Cnr | IRIS Cnr | CNR IRIS 
2024
Conference article
Open Access
BlocklyBias: a visual programming language for bias identification in AI data
De Martino C., Turchi T., Malizia A.
In the current landscape of Artificial Intelligence (AI), bias has emerged as a central concern in both public discourse and scientific inquiry. In today’s rapidly evolving landscape, marked by increasing complexity and challenges, there is a growing need to address the issue of biases and discrimination that can be exacerbated by algorithms. Biases can infiltrate data collection, whether conducted by humans or systems they design, highlighting the multifaceted nature of this challenge. Consequently, addressing this issue from diverse perspectives is imperative, extending its reach beyond technical domains to include stakeholders from various backgrounds. This paper aims to illustrate how the democratization of the data analysis process – specifically regarding intersectional biases – can be achieved through the use of Visual Programming Languages (VPLs). By reducing the technical entry barrier, fostering an understanding of bias, and providing mitigation strategies, this research introduces BlocklyBias, a platform founded on VPL principles. BlocklyBias serves as a foundational stepping stone for future improvements, as a tool to explore and resolve bias-related challenges in data analysis. Through this study, we seek to bridge the gap between technical and non-technical stakeholders, fostering a collaborative approach to bias mitigation in AI.Source: LECTURE NOTES IN COMPUTER SCIENCE, vol. 14735, pp. 45-59. Washington DC, USA, 29/06 – 4/07/2024
DOI: 10.1007/978-3-031-60611-3_4
Metrics:
De Martino C., Turchi T., Malizia A.
In the current landscape of Artificial Intelligence (AI), bias has emerged as a central concern in both public discourse and scientific inquiry. In today’s rapidly evolving landscape, marked by increasing complexity and challenges, there is a growing need to address the issue of biases and discrimination that can be exacerbated by algorithms. Biases can infiltrate data collection, whether conducted by humans or systems they design, highlighting the multifaceted nature of this challenge. Consequently, addressing this issue from diverse perspectives is imperative, extending its reach beyond technical domains to include stakeholders from various backgrounds. This paper aims to illustrate how the democratization of the data analysis process – specifically regarding intersectional biases – can be achieved through the use of Visual Programming Languages (VPLs). By reducing the technical entry barrier, fostering an understanding of bias, and providing mitigation strategies, this research introduces BlocklyBias, a platform founded on VPL principles. BlocklyBias serves as a foundational stepping stone for future improvements, as a tool to explore and resolve bias-related challenges in data analysis. Through this study, we seek to bridge the gap between technical and non-technical stakeholders, fostering a collaborative approach to bias mitigation in AI.Source: LECTURE NOTES IN COMPUTER SCIENCE, vol. 14735, pp. 45-59. Washington DC, USA, 29/06 – 4/07/2024
DOI: 10.1007/978-3-031-60611-3_4
Metrics:
See at:
CNR IRIS | link.springer.com | doi.org | Archivio della Ricerca - Università di Pisa | CNR IRIS | CNR IRIS
2023
Other
Open Access
AIMH Research Activities 2023
Aloia N., Amato G., Bartalesi Lenzi V., Bianchi L., Bolettieri P., Bosio C., Carraglia M., Carrara F., Casarosa V., Ciampi L., Coccomini D. A., Concordia C., Corbara S., De Martino C., Di Benedetto M., Esuli A., Falchi F., Fazzari E., Gennaro C., Lagani G., Lenzi E., Meghini C., Messina N., Molinari A., Moreo Fernandez A., Nardi A., Pedrotti A., Pratelli N., Puccetti G., Rabitti F., Savino P., Sebastiani F., Sperduti G., Thanos C., Trupiano L., Vadicamo L., Vairo C., Versienti L.
The AIMH (Artificial Intelligence for Media and Humanities) laboratory is dedicated to exploring and pushing the boundaries in the field of Artificial Intelligence, with a particular focus on its application in digital media and humanities. This lab's objective is to enhance the current state of AI technology particularly on deep learning, text analysis, computer vision, multimedia information retrieval, multimedia content analysis, recognition, and retrieval. This report encapsulates the laboratory's progress and activities throughout the year 2023.DOI: 10.32079/isti-ar-2023/001
Metrics:
Aloia N., Amato G., Bartalesi Lenzi V., Bianchi L., Bolettieri P., Bosio C., Carraglia M., Carrara F., Casarosa V., Ciampi L., Coccomini D. A., Concordia C., Corbara S., De Martino C., Di Benedetto M., Esuli A., Falchi F., Fazzari E., Gennaro C., Lagani G., Lenzi E., Meghini C., Messina N., Molinari A., Moreo Fernandez A., Nardi A., Pedrotti A., Pratelli N., Puccetti G., Rabitti F., Savino P., Sebastiani F., Sperduti G., Thanos C., Trupiano L., Vadicamo L., Vairo C., Versienti L.
The AIMH (Artificial Intelligence for Media and Humanities) laboratory is dedicated to exploring and pushing the boundaries in the field of Artificial Intelligence, with a particular focus on its application in digital media and humanities. This lab's objective is to enhance the current state of AI technology particularly on deep learning, text analysis, computer vision, multimedia information retrieval, multimedia content analysis, recognition, and retrieval. This report encapsulates the laboratory's progress and activities throughout the year 2023.DOI: 10.32079/isti-ar-2023/001
Metrics:
See at:
CNR IRIS | ISTI Repository | CNR IRIS