A new dataset of claims with conflicting web evidence shows retrieval-augmented LLMs are fragile, and source-credibility cues help only modestly.
Can llm-generated misinformation be detected? In The Twelfth International Conference on Learning Representations, ICLR , 2024
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Resolving Conflicting Evidence in Automated Fact-Checking: A Study on Retrieval-Augmented LLMs
A new dataset of claims with conflicting web evidence shows retrieval-augmented LLMs are fragile, and source-credibility cues help only modestly.