01 / MOTIVATION
Why this work matters
A complete fact-checking article requires more than fluent writing: each cited source must support the statement it is attached to.
A multi-agent fact-checking pipeline that audits citation support with natural language inference.
02 / METHODOLOGY
Research approach
The multi-agent pipeline combines source retrieval, structured article planning, generation, and natural-language-inference citation auditing.
03 / CONTRIBUTIONS
Main contribution
Multi-agent fact-checking with citation auditing via natural-language inference.
Consult the complete publication for numerical findings and experimental qualifications.
04 / PUBLICATION
Read the paper
Farhan Sharukh Hasan, Anirban Saha Anik, Eric Liu, Xiaoying Song, Mohotarema Rashid and Lingzi Hong. (2026). SourceMinds at CheckThat! 2026: NLI-Grounded Citation Auditing in a Multi-Agent Pipeline for Full Fact-Checking Article Generation. Working Notes of CLEF 2026, CEUR Workshop Proceedings, Vol. 4283, pp. 1010–1020.