论文标题
内存辅助提示编辑以改进部署后的GPT-3
Memory-assisted prompt editing to improve GPT-3 after deployment
论文作者
论文摘要
GPT-3等大型LMS具有强大的功能，但可以犯有人类明显的错误。例如，GPT-3会错误地解释“哪个单词与善相似？”是指同句，而用户打算同义词。我们的目标是通过用户与系统的交互有效地纠正此类错误，但没有再进行重新培训，这将是昂贵的。我们将GPT-3与越来越多的记录案例的记忆配对，其中该模型误解了用户的意图以及用户反馈以进行澄清。这样的内存允许我们的系统根据用户反馈对过去的类似情况的错误纠正，为任何新查询产生增强的提示。在四个任务（两个词汇任务，两个高级道德推理任务）上，我们展示了（模拟的）用户如何交互方式教授已部署的GPT-3，从而大大提高了其对查询的准确性，而GPT-3则以不同的误解。我们的方法是朝着非常大的预训练LMS迈出低成本实用程序增强的一步。在https://www.memprompt.com/上实施新任务的备忘录的代码，数据和指令。
Large LMs such as GPT-3 are powerful, but can commit mistakes that are obvious to humans. For example, GPT-3 would mistakenly interpret "What word is similar to good?" to mean a homophone, while the user intended a synonym. Our goal is to effectively correct such errors via user interactions with the system but without retraining, which will be prohibitively costly. We pair GPT-3 with a growing memory of recorded cases where the model misunderstood the user's intents, along with user feedback for clarification. Such a memory allows our system to produce enhanced prompts for any new query based on the user feedback for error correction on similar cases in the past. On four tasks (two lexical tasks, two advanced ethical reasoning tasks), we show how a (simulated) user can interactively teach a deployed GPT-3, substantially increasing its accuracy over the queries with different kinds of misunderstandings by the GPT-3. Our approach is a step towards the low-cost utility enhancement for very large pre-trained LMs. Code, data, and instructions to implement MEMPROMPT for a new task at https://www.memprompt.com/.
