1. Cross-Task Generalization via Natural Language Crowdsourcing Instructions
2. Multitask prompted training enables zero-shot task generalization;Sanh;arXiv preprint arXiv:2110.08207,2021
3. Finetuned language models are zero-shot learners;Wei;arXiv preprint arXiv:2109.01652,2021
4. Training language models to follow instructions with human feedback;Ouyang;arXiv preprint arXiv:2203.02155,2022
5. Improving alignment of dialogue agents via targeted human judgements;Glaese;arXiv preprint arXiv:2209.14375,2022