From Sparse to Dense: GPT-4 Summarization with Chain of Density Prompting
This work addresses the problem of generating optimal summaries for natural language processing applications, though it is incremental as it builds on existing GPT-4 capabilities with a novel prompting technique.
The paper tackled the challenge of balancing informativeness and readability in text summarization by using a Chain of Density prompting method with GPT-4, finding that humans prefer these denser summaries over vanilla prompts and nearly as much as human-written ones on 100 CNN DailyMail articles.
Selecting the ``right'' amount of information to include in a summary is a difficult task. A good summary should be detailed and entity-centric without being overly dense and hard to follow. To better understand this tradeoff, we solicit increasingly dense GPT-4 summaries with what we refer to as a ``Chain of Density'' (CoD) prompt. Specifically, GPT-4 generates an initial entity-sparse summary before iteratively incorporating missing salient entities without increasing the length. Summaries generated by CoD are more abstractive, exhibit more fusion, and have less of a lead bias than GPT-4 summaries generated by a vanilla prompt. We conduct a human preference study on 100 CNN DailyMail articles and find that that humans prefer GPT-4 summaries that are more dense than those generated by a vanilla prompt and almost as dense as human written summaries. Qualitative analysis supports the notion that there exists a tradeoff between informativeness and readability. 500 annotated CoD summaries, as well as an extra 5,000 unannotated summaries, are freely available on HuggingFace (https://huggingface.co/datasets/griffin/chain_of_density).