Know Your Source: A Public Knowledge Store for Media Background Checks
LLM-based retrieval-augmented generation (RAG) is increasingly used for automated fact-checking (AFC) and related tasks. By grounding LLM outputs in retrieved evidence, RAG-based systems provide transparent justifications while allowing external information to be updated independently of the underlying model. However, existing approaches often assume retrieved evidence is reliable, although real-world information may be conflicting, outdated, and can originate from unreliable or biased sources. Recent work on *source-critical reasoning* addresses this challenge through media background checks
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 48%Researchers Demonstrate Chain-of-Thought Spoofing Against LLM Reasoners - Let's Data Science →
- PossiblePossibly related (embedding) · 53%Tencent/WeKnora →
- PossiblePossibly related (embedding) · 47%New tool identifies the sources of fake video - University of California, Riverside →
- PossiblePossibly related (embedding) · 47%New tool identifies the sources of fake videos - University of California, Riverside →
- LinkedLinked via arxiv author · 85%Benjamin Nichols →
“Know Your Source: A Public Knowledge Store for Media Background Checks”
- LinkedLinked via arxiv author · 85%Michael Schlichtkrull →
“Know Your Source: A Public Knowledge Store for Media Background Checks”
- LinkedLinked via arxiv author · 85%Nedjma Ousidhoum →
“Know Your Source: A Public Knowledge Store for Media Background Checks”