From Sparse to Dense: GPT-4 Summarization with Chain of Density Prompting · HackerPapers discussions

From Sparse to Dense: GPT-4 Summarization with Chain of Density Prompting — mentioned by lyu07282

Sun, 21 Jul 2024 22:06:59 GMT

I wouldn't call that an evaluation. They are expressing subjective opinions and feelings, text summarization is an active area of research, there are many benchmark datasets and evaluation measures that make progress quantifiable. Which makes rants like this seem rather pointless and uninformed. Here is an example for something less subjective: https://arxiv.org/abs/2309.04269

Paper and discussion history. A mention is not an endorsement.

From Sparse to Dense: GPT-4 Summarization with Chain of Density Prompting — HN submission

Mon, 13 Nov 2023 21:05:45 GMT

From Sparse to Dense: GPT-4 Summarization with Chain of Density Prompting

2 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

From Sparse to Dense: GPT-4 Summarization with Chain of Density Prompting — mentioned by kevo1ution

Wed, 20 Sep 2023 00:29:49 GMT

The sample paper descriptions could be more concise. Maybe Chain of density (COD) can help here https://arxiv.org/pdf/2309.04269.pdf ?

Paper and discussion history. A mention is not an endorsement.

From Sparse to Dense: GPT-4 Summarization with Chain of Density Prompting — HN submission

Mon, 11 Sep 2023 15:46:05 GMT

From Sparse to Dense: GPT-4 Summarization with Chain of Density Prompting

10 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.