Work

Enhancing Factuality through Consensus and Consistency in Summarization Using Minimum Bayes Risk Decoding

Year: 2026

Type: conference-paper

Abstract: Improving the quality of model-generated summaries, especially factuality, the accuracy of a summary with respect to its source content, remains a challenge.While reranking could select the optimal output from multiple generated candidates, it is limited to only using the source as guidance, resulting in unreliable summaries.To address this limitation, we propose Con-SUM that reranks candidate summaries by considering two factors: consistency to the source document and consensus among the other candidates.Consensus is established using Minimum Bayes Risk (MBR) decoding over the set of generated summaries, while ensuring consistency by employing factuality-aware metrics that compare the summary against the source.Rigorous testing demonstrates that our system is competitive with existing methods, with human evaluations further confirming that its generated summaries are preferred over those from other systems.

Source: Findings of the Association for Computational Linguistics: ACL (Findings of ACL)

DOI: 10.18653/v1/2026.findings-acl.2071

Authors: Riza Setiawan Soetedjo, Yusuke Sakai, Hidetaka Kamigaito, Jingun Kwon, Manabu Okumura, Taro Watanabe

Institutions: Nara Institute of Science and Technology, Chungnam National University, Institute of Science Tokyo

Language: English

Topic: Topic Modeling

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

Funder: Japan Society for the Promotion of Science

OpenAlex ID: W7166826405