SOURCE-LINKED INTELLIGENCE

PageRecall: Measuring Page Selection in Literature-Grounded Question Answering

arXiv · AI, language, vision and robotics · article · Sep 16, 2026 · UTC

We describe our system for LitTraceQA (GroundLM @ EMNLP 2026): given a research question, retrieve the relevant papers from a pool of 27,487, cite the page and the table or figure where the answer lives, and answer in a requested format. Our main finding is that evidence grounding is limited by retrieval, not by reading. The page selector put the annotator's page, which we call the gold page, in front of the model that locates evidence only about half the time (52.6% gold-page recall), while that model, given the page, cited the right one in 45 of the 48 locators it emitted (94%). When the pag

Read original source ↗ Open in workspace

recordType

paper

region

Global