NeFut Logo NeFut
Admin Login

[CS.AI] Authority-Aware Multi-View RAG over Italian Parliamentary Proceedings

Published at: 2026-08-15 22:00 Last updated: 2026-08-16 07:03
#RAG #Authority-Aware #Multi-View #ParliamentRAG #Retrieval-Augmented Generation

Parliamentary proceedings are a primary record of democratic deliberation, yet their volume and fragmentation make multi-perspective access difficult for citizens, journalists, and researchers. Applying Retrieval-Augmented Generation (RAG) to parliamentary transcripts introduces three specific risks: dominance of the most frequent speakers, inability to weight speakers according to topical expertise, and citation misattribution in politically sensitive text. We present ParliamentRAG, a RAG system for the Italian Chamber of Deputies that addresses these risks jointly. Its core contribution is a topic-dependent authority model that estimates each speaker's authority as a function of the current query, combining interpretable components such as profession, education, and previous interventions. Given a user query, the system retrieves relevant speech chunks, identifies topic-relevant experts across parliamentary groups, and generates a summary synthesizing their perspectives, accompanied by supporting quotations. ParliamentRAG is evaluated against Google NotebookLM on 15 policy topics via a two-level protocol combining automated metrics and blind A/B human evaluation by six domain experts. The system achieves higher coverage across political groups (0.97 vs. 0.95), perfect quotation faithfulness (1.00 vs. 0.95), and stronger expert preferences on source-related dimensions, while NotebookLM remains stronger on prose-oriented dimensions. Blogger's Review: ParliamentRAG system effectively addresses the risks of RAG in parliamentary proceedings by introducing a topic-dependent authority model, providing citizens, journalists, and researchers with more accurate and comprehensive information access.

Original Source: https://arxiv.org/abs/2608.13410

[h] Back to Home