Training language models to follow instructions with human feedback
Ouyang et al., 2022, Training language models to follow instructions with human feedback (Advances in Neural Information Processing Systems 35 (NeurIPS 2022))
Subscriber deck — free during early access
1 cards in “4.2 Results on public NLP datasets” · whole deck
4.2 Results on public NLP datasets
- How did InstructGPT change truthfulness, toxicity and bias?More truthful and informative on TruthfulQA, and hallucinating about half as often on closed-domain API tasks (21% vs 41%); about 25% fewer toxic outputs when asked to be respectful, but no advantage without that instruction; no significant improvement on bias benchmarks.
- Ouyang et al., 2022, Training language models to follow instructions with human feedback (Advances in Neural Information Processing Systems 35 (NeurIPS 2022)), §4.2
Source
- Long Ouyang, Jeff Wu, Xu Jiang, Diogo Almeida, Carroll L. Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, John Schulman, Jacob Hilton, Fraser Kelton, Luke Miller, Maddie Simens, Amanda Askell, Peter Welinder, Paul Christiano, Jan Leike and Ryan Lowe. 2022. Training language models to follow instructions with human feedback. In Advances in Neural Information Processing Systems 35 (NeurIPS 2022). https://papers.nips.cc/paper_files/paper/2022/hash/b1efde53be364a73914f58805a001731-Abstract-Conference.html