- How good is GPT-3 at generating human-acceptable free-text explanations?
- Can we produce good explanations with few-shot prompting?
- Can human preference modeling produce even better explanations from GPT-3?

We answer these questions and more in our #NAACL2022 paper. 🧵1/12 “Reframing Human-AI Collaboration for Generating Free-Text Explanations” with @jmhessel @Swabha @mark_riedl @YejinChoinka

Paper: arxiv.org/abs/2112.08674
Code/data: github.com/allenai/few_sh…

Happy to share our new preprint (with @anmarasovic) “Teach Me to Explain: A Review of Datasets for Explainable NLP”
Paper: arxiv.org/abs/2102.12060
Website: exnlpdatasets.github.io

It’s half survey, half reflections for more standardized ExNLP dataset collection. Highlights:

1/6 We focus on datasets of the form: (inputs, labels, explanations). We describe these instance-wise explanations as “explaining human decisions” (the labels). Other types of explanations may explain something about the world. We focus on the shaded area.

2/6