The emergence of large language models (LLMs) has revolutionized machine learning and related fields, showcasing remarkable abilities in comprehending, generating, and manipulating human language. However, their conventional usage through API-based text prompt submissions imposes certain limitations in terms of context constraints and external source availability. To address these challenges, we propose a novel framework called Reinforced Retrieval Augmented Machine Learning (RRAML). RRAML integrates the reasoning capabilities of LLMs with supporting information retrieved by a purpose-built retriever from a vast user-provided database. By leveraging recent advancements in reinforcement learning, our method effectively addresses several critical challenges. Firstly, it circumvents the need for accessing LLM gradients. Secondly, our method alleviates the burden of retraining LLMs for specific tasks, as it is often impractical or impossible due to restricted access to the model and the computational intensity involved. Additionally we seamlessly link the retriever's task with the reasoner, mitigating hallucinations and reducing irrelevant, and potentially damaging retrieved documents. We believe that the research agenda outlined in this paper has the potential to profoundly impact the field of AI, democratizing access to and utilization of LLMs for a wide range of entities.

翻译：大规模语言模型的出现彻底革新了机器学习及相关领域，在理解、生成和操控人类语言方面展现出卓越能力。然而，通过基于API的文本提示提交的传统使用方式，在上下文约束和外部资源可用性方面存在一定局限性。为应对这些挑战，我们提出了一种名为强化检索增强机器学习的新框架。RRAML将大模型的推理能力与由专门构建的检索器从用户提供的海量数据库中检索到的支持信息相结合。通过利用强化学习的最新进展，我们的方法有效解决了若干关键挑战。首先，它规避了访问大模型梯度的需求。其次，我们的方法减轻了特定任务对大模型进行重新训练的负担，因为由于对模型的访问受限及涉及的计算强度大，这通常不切实际或不可行。此外，我们无缝连接了检索器的任务与推理器，减少了幻觉现象，并降低了无关甚至可能有害的检索文档的影响。我们相信，本文概述的研究议程具有深刻影响人工智能领域的潜力，能够使广泛实体更民主化地访问和利用大模型。