你脑子里在想什么？多任务Transformer模型中的涌现行为
What's in your Head? Emergent Behaviour in Multi-Task Transformer Models
摘要：
自然语言处理中多任务训练的主要范例是用共享的预训练语言模型表示输入，并为每个任务添加一个小而薄的网络（头）。给定输入，目标头部是被选择用于输出最终预测的头部。在这项工作中，我们研究了非目标头的行为，也就是说，头的输出时，给定的输入属于一个不同的任务比他们被训练。我们发现，非目标头表现出紧急的行为，这可以解释目标任务，或概括超出他们原来的任务。例如，在数值推理任务中，跨度提取头从输入中提取参数以进行计算，从而产生由目标生成头生成的数字。此外，用目标问答头训练的摘要头在给定问题和要从中提取答案的上下文时输出基于查询的摘要。这种涌现的行为表明，多任务训练会导致技能的非平凡外推，这可以用于解释性和概括性。
英文摘要：
The primary paradigm for multi-task training in natural language processing is to represent the input with a shared pre-trained language model, and add a small, thin network (head) per task. Given an input, a target head is the head that is selected for outputting the final prediction. In this work, we examine the behaviour of non-target heads, that is, the output of heads when given input that belongs to a different task than the one they were trained for. We find that non-target heads exhibit emergent behaviour, which may either explain the target task, or generalize beyond their original task. For example, in a numerical reasoning task, a span extraction head extracts from the input the arguments to a computation that results in a number generated by a target generative head. In addition, a summarization head that is trained with a target question answering head, outputs query-based summaries when given a question and a context from which the answer is to be extracted. This emergent behaviour suggests that multi-task training leads to non-trivial extrapolation of skills, which can be harnessed for interpretability and generalization.
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。
