Tag
This paper examines geographic bias in factual question answering over public companies using retrieval-augmented generation (RAG), revealing that RAG does not uniformly compensate for knowledge gaps and can reinforce disparities.
CorVer is a lightweight, corpus-grounded reward mechanism that uses Wikipedia co-occurrence statistics to provide efficient sentence-level feedback for reinforcement learning in factual question answering, outperforming neural verifiers while training 4.8 to 8.4x faster.