DS@GT ARC at CheckThat! 2026: A Verdict-Anchored Pipeline for Generating Fact-Checking Articles
Paper · https://arxiv.org/abs/2611.05382
arXiv:2611.05382v1 Announce Type: new Abstract: Misinformation spreads faster than professional fact-checkers can manually verify it and write articles explaining their verdicts. This creates a need to automate the production of fact-checking articles. This paper details work done by the DS@GT ARC team for CLEF 2026 CheckThat! Lab Task 3 Fact-Checking Article Generation. We seek to generate a full fact-checking article from a claim, its original verdict, and a set of scraped source documents. Our team built a four-stage pipeline that cleans noisy evidence, retrieves and clusters relevant sources, generates the article by conditioning \texttt{Llama-3.1-8B-Instruct} on the original fact-checker verdict, and recovers inline citations through deterministic post-processing. We achieved a mean score of 0.428 and ranked 3rd out of 9 teams for the CLEF 2026 CheckThat! Lab Task 3, compared to a baseline mean score of 0.272. Our code is available on GitHub at https://github.com/dsgt-arc/checkthat-2026-task3.
First seen by Oriel on .
AI summary
The DS@GT ARC team presents a four-stage pipeline for generating fact-checking articles from claims, verdicts, and scraped sources, placing 3rd of 9 teams in CLEF 2026 CheckThat! Lab Task 3.
- The pipeline cleans noisy evidence, retrieves and clusters relevant sources, generates text with Llama-3.1-8B-Instruct conditioned on the original fact-checker verdict, and restores inline citations deterministically.
- The system achieved a mean score of 0.428, compared with a baseline mean score of 0.272.
- The work addresses automated production of explanatory fact-checking articles from a claim, its verdict, and source documents.
- The team reports that its code is available on GitHub.
#fact-checking #natural language generation #llama
Generated by gpt-5.6-sol. Check the original for details.
Aliases
| Source | External ID | URL |
|---|---|---|
| arXiv AI Papers | oai:arXiv.org:2611.05382v1 | https://arxiv.org/abs/2611.05382 Read discussion |