LinkNav: Surfacing Interconnected Information in Scientific Articles
For researchers reading academic papers, LinkNav helps uncover missed connections, but the work is incremental as it applies existing methods (question generation and answer detection) to a new domain.
LinkNav surfaces connections between non-adjacent passages in scientific articles by generating questions from one passage and searching for answers elsewhere, achieving high precision in answer detection and connecting passages that are on average ten segments apart.
We present LinkNav, an enhanced experience for reading academic papers which makes explicit connections between related but non-adjacent passages. To create the experience, we instruct a language model to generate questions that may arise while reading a passage and then search for answer passages elsewhere in the document, forming intra-document connections when answers are found. We confirm that these building blocks work well to power the experience, with an answer detection pipeline that works with high precision, resulting in a reasonable number of connections being made for a document. On a dataset of academic papers, we find that connected passages are on average ten segments away from each other, making explicit connections that a reader may have otherwise missed.