Prompting has shown impressive success in enabling large pre-trained language models (LMs) to perform diverse NLP tasks, especially with only few downstream data. Automatically finding the optimal prompt for each task, however, is challenging. Most existing work resorts to tuning *soft* prompts (e.g., embeddings) which fall short of interpretability, reusability across LMs, and applicability when gradients are not accessible. *Discrete* prompts, on the other hand, are difficult to optimize, and are often created by “enumeration (e.g., paraphrasing)-then-selection” heuristics that do not explore the prompt space systematically. This paper proposes RLPrompt, an efficient discrete prompt optimization approach with reinforcement learning (RL). RLPrompt formulates a parameter-efficient policy network that generates the optimized discrete prompt after training with reward. To harness the complex and stochastic reward signals from the large LM environment, we incorporate effective reward stabilization that substantially enhances training efficiency. RLPrompt is flexibly applicable to different types of LMs, such as masked (e.g., BERT) and left-to-right models (e.g., GPTs), for both classification and generation tasks. Experiments on few-shot classification and unsupervised text style transfer show superior performance over a wide range of existing fine-tuning or prompting methods. Interestingly, the resulting optimized prompts are often ungrammatical gibberish text; and surprisingly, those gibberish prompts are transferrable between different LMs to retain significant performance, indicating that LM prompting may not follow human language patterns.

We present an interactive Plotting Agent, a system that enables users to directly manipulate plots using natural language instructions within an interactive programming environment. The Plotting Agent maps language to plot updates. We formulate this problem as a slot-based task-oriented dialog problem, which we tackle with a sequence-to-sequence model. This plotting model while accurate in most cases, still makes errors, therefore, the system allows a feedback mode, wherein the user is presented with a top-k list of plots, among which the user can pick the desired one. From this kind of feedback, we can then, in principle, continuously learn and improve the system. Given that plotting is widely used across data-driven fields, we believe our demonstration will be of interest to both practitioners such as data scientists broadly defined, and researchers interested in natural language interfaces.