Relatedly: Scaffolding Literature Reviews with Existing Related Work Sections

TL;DR

This paper introduces Relatedly, a system that aids scholars in navigating and synthesizing related work sections across multiple papers, improving the quality of their literature reviews through dynamic features and auto-generated summaries.

Contribution

The paper presents a novel system, Relatedly, which scaffolds literature review exploration by highlighting dissimilarities, reducing redundancy, and providing descriptive headings to enhance comprehension.

Findings

Scholars using Relatedly produce more coherent outlines.

Relatedly helps identify unexplored research areas.

User study shows improved review quality with Relatedly.

Abstract

Scholars who want to research a scientific topic must take time to read, extract meaning, and identify connections across many papers. As scientific literature grows, this becomes increasingly challenging. Meanwhile, authors summarize prior research in papers' related work sections, though this is scoped to support a single paper. A formative study found that while reading multiple related work paragraphs helps overview a topic, it is hard to navigate overlapping and diverging references and research foci. In this work, we design a system, Relatedly, that scaffolds exploring and reading multiple related work paragraphs on a topic, with features including dynamic re-ranking and highlighting to spotlight unexplored dissimilar information, auto-generated descriptive paragraph headings, and low-lighting of redundant information. From a within-subjects user study (n=15), we found that scholars generate more coherent, insightful, and comprehensive topic outlines using Relatedly compared to a baseline paper list.