ParliamentRAG is a RAG system over the official records of the Italian Chamber of Deputies (19th legislature): 46.8k speech transcripts, 17.3k roll-call votes and 6.9M individual ballots in a Neo4j knowledge graph. Speaker authority is estimated per query (profession, committee work, acts, roles), retrieval is balanced across all parliamentary groups, and every quotation is verified verbatim against the transcript via offset-based retrieval, so fabricated quotes cannot survive. Accepted at ISWC 2026, In-Use track. Dataset: <a href=\"https://huggingface.co/datasets/emeierkeio/parliamentrag-camera-leg19\">https://huggingface.co/datasets/emeierkeio/parliamentrag-camera-leg19</a></p>\n","updatedAt":"2026-08-17T13:45:23.025Z","author":{"_id":"663005ea820da8f8768bc726","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/663005ea820da8f8768bc726/D4MJ4_AD-7Q6q9esn-BKF.jpeg","fullname":"Mirko Tritella","name":"emeierkeio","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.8661049604415894},"editors":["emeierkeio"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/663005ea820da8f8768bc726/D4MJ4_AD-7Q6q9esn-BKF.jpeg"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2608.13410","authors":[{"_id":"6a7f0b5bf747ea94019af4b5","user":{"_id":"663005ea820da8f8768bc726","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/663005ea820da8f8768bc726/D4MJ4_AD-7Q6q9esn-BKF.jpeg","isPro":false,"fullname":"Mirko Tritella","user":"emeierkeio","type":"user","name":"emeierkeio"},"name":"Mirko Tritella","status":"claimed_verified","statusLastChangedAt":"2026-08-14T16:45:04.533Z","hidden":false},{"_id":"6a7f0b5bf747ea94019af4b6","name":"Riccardo Pozzi","hidden":false},{"_id":"6a7f0b5bf747ea94019af4b7","name":"Matteo Palmonari","hidden":false}],"mediaUrls":["https://cdn-uploads.huggingface.co/production/uploads/663005ea820da8f8768bc726/2LYYQr5EpdHu94O9HxDGj.png","https://cdn-uploads.huggingface.co/production/uploads/663005ea820da8f8768bc726/k-Ew2f3dHsu4Y1evcUXMd.png","https://cdn-uploads.huggingface.co/production/uploads/663005ea820da8f8768bc726/hQgg930rnNqPoaiY0tN7w.png"],"publishedAt":"2026-08-13T00:00:00.000Z","submittedOnDailyAt":"2026-08-17T00:00:00.000Z","title":"Who Speaks Matters: Authority-Aware Multi-View RAG over Italian Parliamentary Proceedings","submittedOnDailyBy":{"_id":"663005ea820da8f8768bc726","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/663005ea820da8f8768bc726/D4MJ4_AD-7Q6q9esn-BKF.jpeg","isPro":false,"fullname":"Mirko Tritella","user":"emeierkeio","type":"user","name":"emeierkeio"},"summary":"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.","upvotes":1,"discussionId":"6a7f0b5bf747ea94019af4b8","projectPage":"https://www.parliamentrag.it/","githubRepo":"https://github.com/Emeierkeio/ParliamentRAG","githubRepoAddedBy":"user","ai_summary":"ParliamentRAG is a retrieval-augmented generation system for Italian parliamentary records that uses topic-dependent speaker authority to retrieve expert perspectives and generate faithful, multi-perspective summaries.","ai_keywords":["Retrieval-Augmented Generation","topic-dependent authority model","parliamentary transcripts","quotation faithfulness","expert evaluation"],"ai_summary_model":"thinkingmachines/Inkling-Small","githubStars":2,"organization":{"_id":"67990cdf488b149d61efc411","name":"unimibb","fullname":"University of Milan Bicocca","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/67990c5cb88aa49722e14218/1ENZ5aIp7FaNsXgr5e8q6.png"}},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"663005ea820da8f8768bc726","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/663005ea820da8f8768bc726/D4MJ4_AD-7Q6q9esn-BKF.jpeg","isPro":false,"fullname":"Mirko Tritella","user":"emeierkeio","type":"user"}],"acceptLanguages":["en"],"dailyPaperRank":0,"organization":{"_id":"67990cdf488b149d61efc411","name":"unimibb","fullname":"University of Milan Bicocca","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/67990c5cb88aa49722e14218/1ENZ5aIp7FaNsXgr5e8q6.png"},"query":{}}">

Cite arxiv.org/abs/2608.13410 in a model README.md to link it from this page.

Cite arxiv.org/abs/2608.13410 in a Space README.md to link it from this page.

Add this paper to a collection to link it from this page.