5 papers
Embedding Surgery: Localized Updates for Adaptive Ranking Correction in Dense Retrieval
Maddalena Amendola, Antonio Mallia, Raffaele Perego
Dense retrieval systems are core components of modern search engines, recommendation platforms, and retrieval-augmented generation pipelines. They encode documents and queries into…
Gender Disparities in StackOverflow's Community-Based Question Answering: A Matter of Quantity versus Quality
Maddalena Amendola, Cosimo Rulli, Carlos Castillo +2
Community Question-Answering platforms, such as Stack Overflow (SO), are valuable knowledge exchange and problem-solving resources. These platforms incorporate mechanisms to assess…
Spatially-Enhanced Retrieval-Augmented Generation for Walkability and Urban Discovery
Maddalena Amendola, Chiara Pugliese, Raffaele Perego +1
Large Language Models (LLMs) have become foundational tools in artificial intelligence, supporting a wide range of applications beyond traditional natural language processing, incl…
Understanding and Addressing Gender Bias in Expert Finding Task
Maddalena Amendola, Carlos Castillo, Andrea Passarella +1
The Expert Finding (EF) task is critical in community Question&Answer (CQ&A) platforms, significantly enhancing user engagement by improving answer quality and reducing response ti…
Leveraging Topic Specificity and Social Relationships for Expert Finding in Community Question Answering Platforms
Maddalena Amendola, Andrea Passarella, Raffaele Perego
Online Community Question Answering (CQA) platforms have become indispensable tools for users seeking expert solutions to their technical queries. The effectiveness of these platfo…