The SelectGen Challenge: Finding the Best Training Samples for Few-Shot Neural Text Generation
This work tackles the problem of optimizing annotation budgets and improving benchmarking for few-shot text generation models, though it is incremental as it builds on existing pretrained language model frameworks.
The authors introduced a shared task called SelectGen Challenge to study training instance selection strategies for few-shot neural text generation, addressing the gap where previous work relied on random sampling without systematic investigation of selection methods.
We propose a shared task on training instance selection for few-shot neural text generation. Large-scale pretrained language models have led to dramatic improvements in few-shot text generation. Nonetheless, almost all previous work simply applies random sampling to select the few-shot training instances. Little to no attention has been paid to the selection strategies and how they would affect model performance. The study of the selection strategy can help us to (1) make the most use of our annotation budget in downstream tasks and (2) better benchmark few-shot text generative models. We welcome submissions that present their selection strategies and the effects on the generation quality.