Papers › InFact: A Strong Baseline for Automated Fact-Checking

InFact: A Strong Baseline for Automated Fact-Checking

1 Nov 2024- 2024 11archive 2025-07-28

Mark Rothermel, Tobias Braun, Marcus Rohrbach, Anna Rohrbach

The spread of disinformation poses a global threat to democratic societies, necessitating robust and scalable Automated Fact-Checking (AFC) systems. The AVeriTeC Shared Task Challenge 2024 offers a realistic benchmark for text-based fact-checking methods. This paper presents Information-Retrieving Fact-Checker (InFact), an LLM-based approach that breaks down the task of claim verification into a 6-stage process, including evidence retrieval. When using GPT-4o as the backbone, InFact achieves an AVeriTeC score of 63% on the test set, outperforming all other 20 teams competing in the challenge, and establishing a new strong baseline for future text-only AFC systems. Qualitative analysis of mislabeled instances reveals that InFact often yields a more accurate conclusion than AVeriTeC’s human-annotated ground truth.

PaperPDF

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Claim VerificationFact CheckingRetrieval

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Fact Checking AVeriTeC InFact AveriTeC 0.63 #3 of 3 Archive leaderboard report
Fact Checking AVeriTeC InFact Question + Answer score 0.34 #3 of 3 Archive leaderboard report
Fact Checking AVeriTeC InFact Question Only score 0.45 #3 of 3 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections