Researchers have introduced CAGE, a novel two-stage framework designed to improve the accuracy and faithfulness of inline citations in long-form question answering systems. This approach addresses the challenge of attribution ambiguity by first constructing a cognitive attribution map that explicitly links semantic answer units to supporting documents. Subsequently, a structured citation reasoning model generates sentence-level claims with citations aligned to this map. Experiments on benchmark datasets like ASQA, ELI5, and ExpertQA demonstrate that CAGE achieves state-of-the-art performance in generating verifiable and well-supported answers. AI
IMPACT Improves the reliability and verifiability of AI-generated long-form answers by enhancing citation accuracy.
RANK_REASON The cluster contains an academic paper detailing a new framework and experimental results. [lever_c_demoted from research: ic=1 ai=1.0]
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
