@inproceedings{czajka-etal-2026-amu,
title = "{AMU} at {RAG}4{R}eports 2026 Task {B}: A Practical Multilingual {RAG} Pipeline for Citation-Grounded Reports",
author = "Czajka, Maciej and
Jab{\l}o{\'n}ski, Piotr and
Czajka, Mateusz and
Pierzy{\'n}ski, Konrad and
Jassem, Krzysztof",
editor = "Yang, Eugene and
Lawrie, Dawn and
MacAvaney, Sean and
Mayfield, James and
Soldaini, Luca and
Yates, Andrew",
booktitle = "Proceedings of the 1st Workshop on Multilingual Report Generation via Retrieval Augmented Generation ({RAG}4{R}eports 2026)",
month = jul,
year = "2026",
address = "San Diego, CA, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.rag4reports-1.12/",
pages = "89--93",
ISBN = "979-8-89176-417-0",
abstract = "This system paper presents AMU{'}s submission to RAG4Reports 2026 Task B: a practical multilingual retrieval-augmented generation pipeline for evidence-supported report generation. The system combines full-query retrieval, optional query rewriting, dense retrieval with Qdrant, cross-encoder reranking, diversity-aware context selection, and structured generation. The best submitted run uses BAAI/bge-m3 embeddings, BAAI/bge-reranker-v2-m3 reranking, and gpt-5.1 generation with medium reasoning effort, using a partial-coverage prompt strategy. On the official leaderboard, it achieved F1=0.4351, sentence{\_}support=0.8280, and nugget{\_}coverage=0.3403, indicating that the generated reports were well grounded but only partially comprehensive."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="czajka-etal-2026-amu">
<titleInfo>
<title>AMU at RAG4Reports 2026 Task B: A Practical Multilingual RAG Pipeline for Citation-Grounded Reports</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maciej</namePart>
<namePart type="family">Czajka</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Piotr</namePart>
<namePart type="family">Jabłoński</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mateusz</namePart>
<namePart type="family">Czajka</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Konrad</namePart>
<namePart type="family">Pierzyński</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Krzysztof</namePart>
<namePart type="family">Jassem</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 1st Workshop on Multilingual Report Generation via Retrieval Augmented Generation (RAG4Reports 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Eugene</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dawn</namePart>
<namePart type="family">Lawrie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sean</namePart>
<namePart type="family">MacAvaney</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">James</namePart>
<namePart type="family">Mayfield</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luca</namePart>
<namePart type="family">Soldaini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrew</namePart>
<namePart type="family">Yates</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, CA, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-417-0</identifier>
</relatedItem>
<abstract>This system paper presents AMU’s submission to RAG4Reports 2026 Task B: a practical multilingual retrieval-augmented generation pipeline for evidence-supported report generation. The system combines full-query retrieval, optional query rewriting, dense retrieval with Qdrant, cross-encoder reranking, diversity-aware context selection, and structured generation. The best submitted run uses BAAI/bge-m3 embeddings, BAAI/bge-reranker-v2-m3 reranking, and gpt-5.1 generation with medium reasoning effort, using a partial-coverage prompt strategy. On the official leaderboard, it achieved F1=0.4351, sentence_support=0.8280, and nugget_coverage=0.3403, indicating that the generated reports were well grounded but only partially comprehensive.</abstract>
<identifier type="citekey">czajka-etal-2026-amu</identifier>
<location>
<url>https://aclanthology.org/2026.rag4reports-1.12/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>89</start>
<end>93</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T AMU at RAG4Reports 2026 Task B: A Practical Multilingual RAG Pipeline for Citation-Grounded Reports
%A Czajka, Maciej
%A Jabłoński, Piotr
%A Czajka, Mateusz
%A Pierzyński, Konrad
%A Jassem, Krzysztof
%Y Yang, Eugene
%Y Lawrie, Dawn
%Y MacAvaney, Sean
%Y Mayfield, James
%Y Soldaini, Luca
%Y Yates, Andrew
%S Proceedings of the 1st Workshop on Multilingual Report Generation via Retrieval Augmented Generation (RAG4Reports 2026)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, CA, USA
%@ 979-8-89176-417-0
%F czajka-etal-2026-amu
%X This system paper presents AMU’s submission to RAG4Reports 2026 Task B: a practical multilingual retrieval-augmented generation pipeline for evidence-supported report generation. The system combines full-query retrieval, optional query rewriting, dense retrieval with Qdrant, cross-encoder reranking, diversity-aware context selection, and structured generation. The best submitted run uses BAAI/bge-m3 embeddings, BAAI/bge-reranker-v2-m3 reranking, and gpt-5.1 generation with medium reasoning effort, using a partial-coverage prompt strategy. On the official leaderboard, it achieved F1=0.4351, sentence_support=0.8280, and nugget_coverage=0.3403, indicating that the generated reports were well grounded but only partially comprehensive.
%U https://aclanthology.org/2026.rag4reports-1.12/
%P 89-93
Markdown (Informal)
[AMU at RAG4Reports 2026 Task B: A Practical Multilingual RAG Pipeline for Citation-Grounded Reports](https://aclanthology.org/2026.rag4reports-1.12/) (Czajka et al., RAG4Reports 2026)
ACL