Nostr Web Client

## Introducing GPT-4 Summarization with Chain of Density Prompting

- Researchers from institutions like Columbia University have developed a "Chain of Density" (CoD) prompting method for generating GPT-4 summaries with varying information density.

- The CoD method iteratively incorporates missing salient entities from the original text into the previous summary, making it increasingly entity-dense without changing the summary length.

- Human preference studies show that people prefer denser summaries than those generated by standard GPT-4 prompts, with these summaries being almost as dense as human-written ones.

- The research team conducted human and automatic evaluations on 100 CNN DailyMail articles to better understand the trade-off between informativeness (favoring more entities) and clarity (favoring fewer entities).

- The study provides 500 annotated CoD summaries and an additional 5,000 unannotated summaries for evaluation or distillation.

#AI #LLM #GPT #GPT-4

🔗 Learn more: [2309.04269.pdf](https://ppl-ai-file-upload.s3.amazonaws.com/web/direct-files/1019777/d1249c62-2da9-4810-9797-cac455065e49/2309.04269.pdf)

Reply to this note

Please Login to reply.

Discussion

FWEnoir 2y ago

Chain of Density Prompt

Article: { { ARTICLE} }

You will generate increasingly concise, entity-dense summaries of the above Article.

Repeat the following 2 steps 5 times.

Step 1. Identify 1-3 informative Entities ( ";" delimited) from the Article which are missing from the previously generated summary.

Step 2. Write a new, denser summary of identical length which covers every entity and detail from the previous summary plus the Missing Entities.

A Missing Entity is:

- Relevant: to the main story.

- Specific: descriptive yet concise (5 words or fewer).

- Novel: not in the previous summary.

- Faithful: present in the Article.

- Anywhere: located anywhere in the Article.

Guidelines:

- The first summary should be long (4-5 sentences, ~80 words) yet highly non-specific, containing little information beyond the entities marked as missing. Use overly verbose language and fillers (e.g., "this article discusses") to reach ~80 words. - Make every word count: rewrite the previous summary to improve flow and make space for additional entities.

- Make space with fusion, compression, and removal of uninformative phrases like "the article discusses".

- The summaries should become highly dense and concise yet self-contained, e.g., easily understood without the Article. - Missing entities can appear anywhere in the new summary.

- Never drop entities from the previous summary. If space cannot be made, add fewer new entities.

Remember, use the exact same number of words for each summary.

Answer in JSON. The JSON should be a list (length 5) of dictionaries whose keys are "Missing_Entities" and "Denser_Summary.