Bowen Song

Achieving high-quality model performance with just 10% of the required labels could revolutionize the scalability of RLVR in large language models.

Despite high rationale identification, search-augmented models struggle with refusal, achieving only 42.9% correct halting on unanswerable multi-hop questions.

EviSD achieves state-of-the-art performance in question-answering tasks by leveraging privileged evidence, outperforming existing methods while maintaining efficiency in response generation.