Symbol tuning improves in-context learning in language models — mentioned by heliophobicdude

Tue, 30 May 2023 18:29:55 GMT

This is great! Addressing the model limitations a bit: in the demonstration data that is provided to the base model, we should prevent computed or "looked up" answers. I've seen some of the demonstration data that people are using to train instruction-tuned models and are being taught to respond by making up answers to solutions it shouldn't try to compute. Btw, the output is wrong. { "instruction": "What would be the output of the following JavaScript snippet?", "input": "let area = 6 * 5;\nlet radius = area / 3.14;", "output": "The output of the JavaScript snippet is the radius, which is…

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

Symbol tuning improves in-context learning in language models — HN submission

Wed, 17 May 2023 00:37:24 GMT

Symbol tuning improves in-context learning in language models

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

Symbol tuning improves in-context learning in language models · HackerPapers discussions

Symbol tuning improves in-context learning in language models — mentioned by heliophobicdude

Symbol tuning improves in-context learning in language models — HN submission