Two mid-trained small language models (350M and 1B) are claimed to achieve state-of-the-art RAG accuracy in their size class while generating native literal-quote citations.
Introducing Citations on the Anthropic API , 2025 b
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Even Small Reasoners Should Quote Their Sources: Introducing the Pleias-RAG Model Family
Two mid-trained small language models (350M and 1B) are claimed to achieve state-of-the-art RAG accuracy in their size class while generating native literal-quote citations.