Probing Classifiers: Promises, Shortcomings, and Advances — mentioned by awinter-py

Mon, 20 Mar 2023 21:39:45 GMT

> asked GPT to take 175 human-written instruction/output pairs, and start generating more in the same style and format ... through one of OpenAI's helpfully provided APIs, and ... the team had some 52,000 sample conversations to use in post-training the LLaMA model hmm I wonder if this is essentially a probe[1] technique + relies on chatgpt already having been extensively trained like did they basically exfiltrate the weights 1. probing per https://arxiv.org/abs/2102.12452

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

Probing Classifiers: Promises, Shortcomings, and Advances · HackerPapers discussions

Probing Classifiers: Promises, Shortcomings, and Advances — mentioned by awinter-py