A Question Answering Framework for Decontextualizing User-facing Snippets from Scientific Documents
This addresses the issue of decontextualized snippets being hard to understand for users in applications like note-taking and search, but it is incremental as it builds on existing language model capabilities.
The paper tackles the problem of making snippets from scientific documents understandable on their own by using language models to rewrite them, resulting in a prompting strategy called QaDecontext that improves over end-to-end methods, though challenges in question generation and answering persist.
Many real-world applications (e.g., note taking, search) require extracting a sentence or paragraph from a document and showing that snippet to a human outside of the source document. Yet, users may find snippets difficult to understand as they lack context from the original document. In this work, we use language models to rewrite snippets from scientific documents to be read on their own. First, we define the requirements and challenges for this user-facing decontextualization task, such as clarifying where edits occur and handling references to other documents. Second, we propose a framework that decomposes the task into three stages: question generation, question answering, and rewriting. Using this framework, we collect gold decontextualizations from experienced scientific article readers. We then conduct a range of experiments across state-of-the-art commercial and open-source language models to identify how to best provide missing-but-relevant information to models for our task. Finally, we develop QaDecontext, a simple prompting strategy inspired by our framework that improves over end-to-end prompting. We conclude with analysis that finds, while rewriting is easy, question generation and answering remain challenging for today's models.