With direct access to human-written reference as memory, retrieval-augmented generation has achieved much progress in a wide range of text generation tasks. Since better memory would typically prompt better generation~(we define this as primal problem), previous works mainly focus on how to retrieve better memory. However, one fundamental limitation exists for current literature: the memory is retrieved from a fixed corpus and is bounded by the quality of the corpus. Due to the finite retrieval space, bounded memory would greatly limit the potential of the memory-augmented generation model. In this paper, by exploring the duality of the primal problem: better generation also prompts better memory, we propose a framework called Selfmem, which iteratively adopts a retrieval-augmented generator itself to generate an unbounded memory pool and uses a memory selector to pick one generated memory for the next generation round. By combining the primal and dual problem, a retrieval-augmented generation model could lift itself up with its own output in the infinite generation space. To verify our framework, we conduct extensive experiments across various text generation scenarios including neural machine translation, abstractive summarization and dialogue generation over seven datasets and achieve state-of-the-art results in JRC-Acquis(four directions), XSum(50.3 ROUGE-1) and BigPatent(62.9 ROUGE-1).

翻译：通过直接访问人工编写的参考记忆，检索增强生成在广泛的文本生成任务中取得了显著进展。由于更好的记忆通常会促进更好的生成（我们将此定义为主要问题），先前的工作主要关注如何检索更优的记忆。然而，当前文献存在一个基本限制：记忆是从固定语料库中检索的，并受限于语料库的质量。由于检索空间有限，受限的记忆会极大限制记忆增强生成模型的潜力。本文通过探索主要问题的对偶性——更好的生成也促进更好的记忆，提出了一种名为Selfmem的框架。该框架迭代地使用检索增强生成器本身生成无限记忆池，并通过记忆选择器为下一轮生成挑选一个生成的记忆。通过结合主要问题与对偶问题，检索增强生成模型能够在无限生成空间中借助自身输出实现自我提升。为验证该框架，我们在神经机器翻译、抽象式摘要和对话生成等多种文本生成场景中进行了广泛实验，涵盖七个数据集，并在JRC-Acquis（四个方向）、XSum（50.3 ROUGE-1）和BigPatent（62.9 ROUGE-1）上取得了最先进的结果。