Metraipolis › archive › dc_ceb4359ba687

Who Speaks Matters: Authority-Aware Multi-View RAG over Italian Parliamentary Proceedings — arXiv:2608.13410

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.13410
License (as archived)
CC0-1.0
Archived
2026-10-19T04:17:41.393Z
SHA-256 of the archived text
eb99682c8100d4817ea332678ce66abd584747a5f847d3013967f5009d0dde3c
Stable URL of this page
https://metraipolis.com/documento/dc_ceb4359ba687

How to cite

Who Speaks Matters: Authority-Aware Multi-View RAG over Italian Parliamentary Proceedings — arXiv:2608.13410 — arXiv (en), https://arxiv.org/abs/2608.13410 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ceb4359ba687 (Metraipolis archive dc_ceb4359ba687, sha256 eb99682c8100d4817ea332678ce66abd584747a5f847d3013967f5009d0dde3c)
BibTeX
@misc{dcceb4359ba687,
  title = {Who Speaks Matters: Authority-Aware Multi-View RAG over Italian Parliamentary Proceedings — arXiv:2608.13410},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.13410},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ceb4359ba687; sha256 eb99682c8100d4817ea332678ce66abd584747a5f847d3013967f5009d0dde3c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.13410. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-14 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.13410 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-19T04:13:06.615Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).