Demystifying Prompts in Language Models via Perplexity Estimation — mentioned by mm321

Sat, 13 May 2023 06:15:10 GMT

I don't understand this whole business of page long prompts, the following article says that this kind of short LLM prompts work the best - and they actually measured the performance of the different kinds of prompts! https://arxiv.org/pdf/2212.04037.pdf "we devise the following straightforward procedure: 1. Obtain a small set of manually created prompts for the task. 2. Expand the set of prompts with automatic paraphrasing using a LM (e.g., GPT3) and backtranslation (see Section 3). 3. Rank the list of prompts by perplexity (aver- aged on a representative sample of task inputs, e.g. 1,000).…

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

Demystifying Prompts in Language Models via Perplexity Estimation — HN submission

Sat, 13 May 2023 04:19:53 GMT

Do the simplest LLM prompts work best?

1 point; 1 discussion reply on HN. Paper and source history. A submission is not an endorsement.

Demystifying Prompts in Language Models via Perplexity Estimation · HackerPapers discussions

Demystifying Prompts in Language Models via Perplexity Estimation — mentioned by mm321

Demystifying Prompts in Language Models via Perplexity Estimation — HN submission