发言者至关重要：基于权威感知的多视角RAG在意大利议会 proceedings 中的应用

摘要

议会程序是民主审议的主要记录，然而其体量庞大且内容零散，使公民、记者和研究人员难以从多视角进行查阅。将检索增强生成（RAG）应用于议会记录会带来三个特定风险：最频繁发言者的主导效应、无法根据议题专长对发言者进行加权，以及政治敏感文本中的引文归属错误。我们提出ParliamentRAG，一个针对意大利众议院的RAG系统，旨在共同应对这些风险。其核心贡献在于一个依赖主题的权威模型，该模型根据当前查询估计每位发言者的权威度，整合了职业、教育背景和既往发言等可解释组件。给定用户查询，系统检索相关发言片段，识别各议会党团中与议题相关的专家，并生成综合各方观点的摘要，附带支持性引文。ParliamentRAG在15个政策议题上与Google NotebookLM进行对比评估，采用结合自动指标和六位领域专家盲法A/B人工评估的两级协议。该系统在政治团体覆盖度上更高（0.97对0.95），引文忠实度达到完美水平（1.00对0.95），并在来源相关维度上获得更强的专家偏好，而NotebookLM在行文导向维度上仍占优势。

English

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.