Who Speaks Matters: Authority-Aware Multi-View RAG over Italian Parliamentary Proceedings
On the map: Retrieval-augmented generation → Legal and financial RAG
Abstract (arXiv)
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.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Legal and financial RAG, one of 15 directions in Retrieval-augmented generation. Builds on 9 of its 28 references that are in the map. First posted on arXiv 13 Aug 2026.
Builds on
9 of 28 references.
References · 9
- 2022Survey of Hallucination in Natural Language Generationcited by 2,075
- 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 1,453
- 2024Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preferencecited by 1,184
- 2020On Faithfulness and Factuality in Abstractive Summarizationcited by 900
- 2023Whose Opinions Do Language Models Reflect?cited by 773
- 2023Evaluating Verifiability in Generative Search Enginescited by 303
- 2022RARR: Researching and Revising What Language Models Say, Using Language Modelscited by 287
- 2021Measuring Attribution in Natural Language Generation Modelscited by 256
- 2017FA*IR: A Fair Top-k Ranking Algorithmcited by 113
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2025PolicyBot - Reliable Question Answering over Policy Documents
- 2026Transcription and Recognition of Italian Parliamentary Speeches Using Vision-Language Models
- 2025DebateBench: A Challenging Long Context Reasoning Benchmark For Large Language Models
- 2025Agent-Enhanced Large Language Models for Researching Political Institutions
- 2025A Greek Government Decisions Dataset for Public-Sector Analysis and Insight
- 2026Graph-Augmented LLMs for Swiss MP Ideology Prediction
- 2024Investigating LLMs as Voting Assistants via Contextual Augmentation: A Case Study on the European Parliament Elections 2024
- 2024RAGAR, Your Falsehood Radar: RAG-Augmented Reasoning for Political Fact-Checking using Multimodal Large Language Models