--- title: "GenAIus at RAG4Reports 2026: Citation-Aware Compression for" description: "The paper presents the GenAIus team's entry to the RAG4Reports 2026 Multilingual Report Generation Task. 5 references." authors: ["Reyyan Yeniterzi", "Suveyda Yeniterzi"] year: 2026 venue: "Proceedings of the 1st Workshop on Multilingual Report Generation via Retrieval Augmented Generation (RAG4Reports 2026)" source: "https://aclanthology.org/2026.rag4reports-1.11/" doi: "10.18653/v1/2026.rag4reports-1.11" licence: "CC BY 4.0 (ACL Anthology)" licence_url: "https://creativecommons.org/licenses/by/4.0/" summary_licence: "Elamur Cosmic License" canonical: "https://research.elamur.ai/free/en/papers/yeniterzi-2026-genaius-rag4reports-2026-citation-aware/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/yeniterzi-2026-genaius-rag4reports-2026-citation-aware/) [home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/34/) / GenAIus at RAG4Reports 2026: Citation-Aware Compression for Multilingual Report Generation # GenAIus at RAG4Reports 2026: Citation-Aware Compression for Multilingual Report Generation **Authors:** [Reyyan Yeniterzi](https://md.research.elamur.ai/free/en/authors/reyyan-yeniterzi/) and [Suveyda Yeniterzi](https://md.research.elamur.ai/free/en/authors/suveyda-yeniterzi/) · **Year:** 2026 · **Venue:** [Proceedings of the 1st Workshop on Multilingual Report Generation via Retrieval Augmented Generation (RAG4Reports 2026)](https://md.research.elamur.ai/free/en/venues/rag4reports/) ([Workshop on Multilingual Report Generation via Retrieval Augmented Generation 2026](https://md.research.elamur.ai/free/en/venues/rag4reports/2026/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/) **Links:** [Publisher's page](https://aclanthology.org/2026.rag4reports-1.11/) · [PDF](https://aclanthology.org/2026.rag4reports-1.11.pdf) · [DOI 10.18653/v1/2026.rag4reports-1.11](https://doi.org/10.18653/v1/2026.rag4reports-1.11) · [OpenAlex](https://openalex.org/W7166839486) **Citations:** 0 citations (OpenAlex, 2026-10-14) ## Summary The paper presents the GenAIus team's entry to the RAG4Reports 2026 Multilingual Report Generation Task. In this task, English report requests must be answered with reports in which every sentence is backed by citations to a news corpus in English, Chinese, Russian and Arabic. The topics overlapped with those of TREC 2025 RAGTIME, so the authors kept their earlier evidence pipeline fixed and reused its outputs: question decomposition, multilingual retrieval with cross-question score aggregation, LLM-extracted nuggets, and LLM-based thematic clustering. They changed only the writing stage. Instead of producing the short and long reports separately, the system first writes the long report from the clustered nuggets. It then edits that report down to the short version, keeping the most important claims and only the citations that still support them. All runs relied on prompting alone, with no fine-tuning. With GPT-4o, this compression approach placed second on the leaderboard and improved both citation support and coverage over the team's independent-generation baseline. The result suggests that length-constrained grounded reporting benefits from separating synthesis from content selection. ## Key points - The corpus was sampled from Common Crawl News (2021–2024) in four languages. Evaluation used the Auto-ARGUE framework, which scores how well reports cover nuggets and how well their sentences are backed by citations, along with an F1 that combines the two. - The baseline run, trial (GPT-4o, reports generated independently, as in the earlier genaius-cluster TREC run), ranked 3rd with F1 0.5382, sentence support 0.7936 and nugget coverage 0.4395. - The best run, genaius-cluster-gpt4 (GPT-4o, long report then citation-aware compression), ranked 2nd with F1 0.5456, support 0.8140 and coverage 0.4428. - The genaius-cluster-gpt5 run swapped in GPT-5.4. It reached the highest coverage (0.4487), but its support fell to 0.6620, giving F1 0.5006 and 5th place. This illustrates the tradeoff between coverage and citation faithfulness. - Future work will focus on stronger citation verification and on systematic ablations of the generation stage. *Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.* 📚 Shelves (6): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 18,614 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 17,965 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 17,450 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 17,296 works · [👁️ Computer Vision and Pattern Recognition](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) · 3,486 works · [🗄️ Information Systems](https://md.research.elamur.ai/free/en/shelves/computer-science/information-systems/) · 1,730 works 🧭 Topics (2): [🌍 Multilingual & cross-lingual NLP](https://md.research.elamur.ai/free/en/topics/multilingual-nlp/) · 882 works · [🪶 Efficient models & compression](https://md.research.elamur.ai/free/en/topics/efficient-models/) · 297 works ## Cite Cite as: Reyyan Yeniterzi and Suveyda Yeniterzi. 2026. GenAIus at RAG4Reports 2026: Citation-Aware Compression for Multilingual Report Generation. Proceedings of the 1st Workshop on Multilingual Report Generation via Retrieval Augmented Generation (RAG4Reports 2026). The paper itself, not this page. BibTeX from the library's record of the work. ```bibtex @inproceedings{yeniterzi2026genaius, title = {{GenAIus at RAG4Reports 2026: Citation-Aware Compression for Multilingual Report Generation}}, author = {Reyyan Yeniterzi and Suveyda Yeniterzi}, booktitle = {Proceedings of the 1st Workshop on Multilingual Report Generation via Retrieval Augmented Generation (RAG4Reports 2026)}, year = {2026}, doi = {10.18653/v1/2026.rag4reports-1.11}, url = {https://doi.org/10.18653/v1/2026.rag4reports-1.11} } ``` - [← previous GCIG: GraphRAG-based Cross-document Instruction Generation for Boosting LLM Reasoning](https://md.research.elamur.ai/free/en/papers/xu-2026-gcig-graphrag-based-cross-document/) - [next → Gender and Politeness Perception: A Novel Approach for Exploring Annotations Disagreement](https://md.research.elamur.ai/free/en/papers/aljanaideh-2026-gender-politeness-perception-novel-approach/) - [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/34/) ## References 5 references, 0 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet. 1. Dawn Lawrie, Sean MacAvaney, James Mayfield, Luca Soldaini, Eugene Yang, and Andrew Yates. 2025. Overview of the TREC 2025 RAGTIME track. In Proceedings of the 34th Text REtrieval Conference (TREC 2025). [find](https://scholar.google.com/scholar?q=Dawn+Lawrie%2C+Sean+MacAvaney%2C+James+Mayfield%2C+Luca+Soldaini%2C+Eugene+Yang%2C+and+Andrew+Yates%2E+2025%2E+Overview+of+the+TREC+2025+RAGTIME+track%2E+In+Proceedings+of+the+34th+Text+REtrieval+Conference+%28TREC+202) 2. OpenAI. 2024. Gpt-4o. https://developers. Ac-openai.com/api/docs/models/gpt-4o. cessed: 2026-03-10. [find](https://scholar.google.com/scholar?q=OpenAI%2E+2024%2E+Gpt%2D4o%2E+https%3A%2F%2Fdevelopers%2E+Ac%2Dopenai%2Ecom%2Fapi%2Fdocs%2Fmodels%2Fgpt%2D4o%2E+cessed%3A+2026%2D03%2D10%2E) 3. OpenAI. 2026. Gpt-5.4. [https://developers.openai.com/api/docs/models/gpt-5.4](https://developers.openai.com/api/docs/models/gpt-5.4). Accessed: 2026-03-10. [↗](https://developers.openai.com/api/docs/models/gpt-5.4) 4. William Walden, Marc Mason, Orion Weller, Laura Dietz, John Conroy, Neil Molino, Hannah Recknor, Bryan Li, Gabrielle Kaili-May Liu, Yu Hou, Dawn Lawrie, James Mayfield, and Eugene Yang. 2026. Auto-argue: Llm-based report generation evaluation. Preprint, arXiv:2509.26184. — [arXiv:2509.26184](https://arxiv.org/abs/2509.26184) [find](https://scholar.google.com/scholar?q=William+Walden%2C+Marc+Mason%2C+Orion+Weller%2C+Laura+Dietz%2C+John+Conroy%2C+Neil+Molino%2C+Hannah+Recknor%2C+Bryan+Li%2C+Gabrielle+Kaili%2DMay+Liu%2C+Yu+Hou%2C+Dawn+Lawrie%2C+James+Mayfield%2C+and+Eugene+Yang%2E+2026%2E+Auto%2Darg) 5. Suveyda Yeniterzi and Reyyan Yeniterzi. 2025. Question-driven multilingual retrieval and report generation for the ragtime track at trec 2025. In Proceedings of the 34th Text REtrieval Conference (TREC 2025). [find](https://scholar.google.com/scholar?q=Suveyda+Yeniterzi+and+Reyyan+Yeniterzi%2E+2025%2E+Question%2Ddriven+multilingual+retrieval+and+report+generation+for+the+ragtime+track+at+trec+2025%2E+In+Proceedings+of+the+34th+Text+REtrieval+Conference+%28TRE) *Updated 2 November 2026*