Crucible @ Rag4Reports: Generating Nuggets for Report Generation and Evaluation

Laura Dietz, Eugene Yang


Abstract
We submit to both tracks of the RAG4Reports challenge with two complementary components: PREFNUGGET, which derives concise nugget banks from pairwise preference judgments between system responses, and CRUCIBLE, a nugget-first pipeline that uses such banks to assemble reports on a given topic. The shared nugget-level representation unifies our approach to report evaluation (Task A) and report generation (Task B).
Anthology ID:
2026.rag4reports-1.10
Volume:
Proceedings of the 1st Workshop on Multilingual Report Generation via Retrieval Augmented Generation (RAG4Reports 2026)
Month:
July
Year:
2026
Address:
San Diego, CA, USA
Editors:
Eugene Yang, Dawn Lawrie, Sean MacAvaney, James Mayfield, Luca Soldaini, Andrew Yates
Venues:
RAG4Reports | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
77–82
Language:
URL:
https://preview.aclanthology.org/ingest-acl-workshops/2026.rag4reports-1.10/
DOI:
Bibkey:
Cite (ACL):
Laura Dietz and Eugene Yang. 2026. Crucible @ Rag4Reports: Generating Nuggets for Report Generation and Evaluation. In Proceedings of the 1st Workshop on Multilingual Report Generation via Retrieval Augmented Generation (RAG4Reports 2026), pages 77–82, San Diego, CA, USA. Association for Computational Linguistics.
Cite (Informal):
Crucible @ Rag4Reports: Generating Nuggets for Report Generation and Evaluation (Dietz & Yang, RAG4Reports 2026)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingest-acl-workshops/2026.rag4reports-1.10.pdf