论文标题
不要产生，歧视：将语言模型接地到现实世界环境的建议
Don't Generate, Discriminate: A Proposal for Grounding Language Models to Real-World Environments
论文作者
论文摘要
当前语言模型（LMS）的关键缺失能力正在实现现实环境。基础语言理解的大多数现有工作都使用LMS直接生成可以在环境中执行的计划以实现所需的效果。因此，它赋予了LMS上的语法，忠诚和可控性的负担。我们提出了Pangu，这是一个通用的语言理解的通用框架，它利用了LMS的歧视能力而不是其生成能力。 Pangu由符号代理和以协同方式工作的神经LM组成：代理商探索了逐步构建有效计划的环境，LM评估了候选人计划指导搜索过程的合理性。具有庞大环境的知识基础问题回答问题（KBQA）的挑战性问题的案例研究表明，pangu的有效性和灵活性：bert-base LM足以在标准的KBQA数据集中设定新记录，而较大的LMS则进一步带来了可观的收益。 Pangu还可以首次启用使用大型LMS（例如Codex）的KBQA的有效的几射击中下文学习。
A key missing capacity of current language models (LMs) is grounding to real-world environments. Most existing work for grounded language understanding uses LMs to directly generate plans that can be executed in the environment to achieve the desired effects. It thereby casts the burden of ensuring grammaticality, faithfulness, and controllability all on the LMs. We propose Pangu, a generic framework for grounded language understanding that capitalizes on the discriminative ability of LMs instead of their generative ability. Pangu consists of a symbolic agent and a neural LM working in a concerted fashion: The agent explores the environment to incrementally construct valid plans, and the LM evaluates the plausibility of the candidate plans to guide the search process. A case study on the challenging problem of knowledge base question answering (KBQA), which features a massive environment, demonstrates the remarkable effectiveness and flexibility of Pangu: A BERT-base LM is sufficient for setting a new record on standard KBQA datasets, and larger LMs further bring substantial gains. Pangu also enables, for the first time, effective few-shot in-context learning for KBQA with large LMs such as Codex.
