Meta-learning and few-shot prompting are viable methods to induce certain types of compositional behaviour. However, these methods can be very sensitive to the choice of support examples used. Choosing good supports from the training data for a given test query is already a difficult problem, but in some cases solving this may not even be enough. We consider a grounded language learning problem (gSCAN) where good support examples for certain test splits might not even exist in the training data, or would be infeasible to search for. We design an agent which instead generates possible supports which are relevant to the test query and current state of the world, then uses these supports via meta-learning to solve the test query. We show substantially improved performance on a previously unsolved compositional behaviour split without a loss of performance on other splits. Further experiments show that in this case, searching for relevant demonstrations even with an oracle function is not sufficient to attain good performance when using meta-learning.

翻译：元学习和少样本提示是诱导特定类型组合行为的可行方法。然而，这些方法对支撑示例的选择非常敏感。针对给定测试查询从训练数据中选择合适的支撑已是一个难题，但在某些情况下，仅解决此问题可能仍不够。我们考虑了一个基于语境的语言学习问题（gSCAN），其中某些测试分区的良好支撑示例可能在训练数据中根本不存在，或难以通过搜索获取。我们设计了一个智能体，它能够生成与测试查询及当前世界状态相关的潜在支撑，并通过元学习利用这些支撑来解决测试查询。实验表明，在一个此前未解决的组合行为分区上，我们取得了显著的性能提升，且未在其他分区上造成性能损失。进一步实验显示，在此情况下，即便使用预言函数搜索相关示例，也不足以在元学习中取得良好性能。