$L^*LM$:使用自然语言预言机从示例中学习自动机
$L^*LM$: Learning Automata from Examples using Natural Language Oracles
AI总结:
提出$L^*LM$算法,结合专家演示与自然语言,利用大语言模型回答成员查询,显著提升从演示中学习确定性有限自动机的数据效率,实现少样本学习。
摘要:
专家演示已被证明是一种间接指定复杂任务的简便方式。最近的算法甚至支持从演示中提取明确的正式规范,例如确定性有限自动机(DFA)。不幸的是,这些技术通常样本效率不高。在这项工作中,我们引入了 $L^*LM$,一种从演示和自然语言中学习DFA的算法。由于自然语言的表达能力,我们观察到从专家演示中学习DFA的数据效率有了显著提高。在技术上,$L^*LM$ 利用大型语言模型来回答关于底层任务的成员查询。然后,这结合了最近的技术,将演示学习转化为一系列标记示例学习问题。在我们的实验中,我们观察到这两种模态相互补充,产生了一个强大的少样本学习者。
英文摘要:
Expert demonstrations have proven an easy way to indirectly specify complex tasks. Recent algorithms even support extracting unambiguous formal specifications, e.g. deterministic finite automata (DFA), from demonstrations. Unfortunately, these techniques are generally not sample efficient. In this work, we introduce $L^*LM$, an algorithm for learning DFAs from both demonstrations and natural language. Due to the expressivity of natural language, we observe a significant improvement in the data efficiency of learning DFAs from expert demonstrations. Technically, $L^*LM$ leverages large language models to answer membership queries about the underlying task. This is then combined with recent techniques for transforming learning from demonstrations into a sequence of labeled example learning problems. In our experiments, we observe the two modalities complement each other, yielding a powerful few-shot learner.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。