2022 LargeLanguageModelsAreHumanLeve
- (Zhou et al., 2022) ⇒ Yongchao Zhou, Andrei Ioan Muresanu, Ziwen Han, Keiran Paster, Silviu Pitis, Harris Chan, and Jimmy Ba. (2022). “Large Language Models Are Human-level Prompt Engineers.” In: arXiv preprint arXiv:2211.01910.
Subject Headings: LM Prompt Engineering, Automatic Prompt Engineer (APE).
Notes
Cited By
Quotes
Abstract
By conditioning on natural language instructions, large language models (LLMs) have displayed impressive capabilities as general-purpose computers. However, task performance depends significantly on the quality of the prompt used to steer the model, and most effective prompts have been handcrafted by humans. Inspired by classical program synthesis and the human approach to prompt engineering, we propose Automatic Prompt Engineer (APE) for automatic instruction generation and selection. In our method, we treat the instruction as the “program," optimized by searching over a pool of instruction candidates proposed by an LLM in order to maximize a chosen score function. To evaluate the quality of the selected instruction, we evaluate the zero-shot performance of another LLM following the selected instruction. Experiments on 24 NLP tasks show that our automatically generated instructions outperform the prior LLM baseline by a large margin and achieve better or comparable performance to the instructions generated by human annotators on 19/24 tasks. We conduct extensive qualitative and quantitative analyses to explore the performance of APE. We show that APE-engineered prompts can be applied to steer models toward truthfulness and/or informativeness, as well as to improve few-shot learning performance by simply prepending them to standard in-context learning prompts. Please check out our webpage at [this https URL.
1. Introduction
The combination of scale and attention-based architectures has resulted in language models possessing an unprecedented level of generality (Kaplan et al., 2020; Vaswani et al., 2017). These so-called “large language models” (LLMs) have shown remarkable, often superhuman, capabilities across a diverse range of tasks, including both zero-shot and few-shot setups (Brown et al., 2020; Srivastava et al., 2022). With generality, however, there comes a question of control: how can we make LLMs do what we want them to do?
To answer this question and steer LLMs toward desired behaviors, recent work has considered fine-tuning (Ouyang et al., 2022; Ziegler et al., 2019), in-context learning (Brown et al., 2020), and several forms of prompt generation (Gao, 2021), including both differentiable tuning of soft prompts (Qin & Eisner, 2021; Lester et al., 2021) and natural language prompt engineering (Reynolds & McDonell, 2021). The latter is of particular interest, as it provides a natural interface for humans to communicate with machines and may be of great relevance not only to LLMs but to other generalist models such as prompted image synthesizers (Rombach et al., 2022; Ramesh et al., 2022), for which public interest in prompt design and generation has also emerged (see Appendix A for examples).
Behind this interest is the fact that plain language prompts do not always produce the desired results, even when those results are possible to produce with alternative instructions. Thus, human users must experiment with a wide range of prompts to elicit desired behaviors, as they have little knowledge of how compatible instructions are with a particular model. We can understand this by viewing LLMs as black-box computers that execute programs specified by natural language instructions: while they can execute a broad range of natural language programs, the way these programs are processed may not be intuitive for humans, and the quality of instruction can only be measured when executing these instructions on a downstream task (Sanh et al., 2022; Wei et al., 2021).
To reduce the human effort involved in creating and validating effective instructions, we propose a novel algorithm using LLMs to generate and select instructions automatically. We call this problem Figure 1: (a) Natural language program synthesis finds an appropriate instruction (the program) that generates the observed demonstrations when executed by the model. We frame this as a black-box optimization problem guided by an inference procedure. (b) We use LLMs as inference models to fill in the blank; our algorithm involves a search over candidates proposed by the inference models. (c) As measured by the interquartile mean across the 24 NLP tasks introduced by Honovich et al. (2022), APE is able to surpass human performance when using the InstructGPT model (Ouyang et al., 2022). natural language program synthesis and propose to address it as a black-box optimization problem using LLMs to generate and search over heuristically viable candidate solutions. In doing so, we leverage the generalist capabilities of LLMs in three ways. First, we use an LLM as an inference model (Ellis et al., 2021; Honovich et al., 2022) to generate instruction candidates based on a small set of demonstrations in the form of input-output pairs. Next, we guide the search process by computing a score for each instruction under the LLM we seek to control. Finally, we propose an iterative Monte Carlo search method where LLMs improve the best candidates by proposing semantically similar instruction variants. Intuitively, our algorithm asks LLMs to generate a set of instruction candidates based on demonstrations and then asks them to assess which instructions are more promising. We call our algorithm Automatic Prompt Engineer (APE). Our main contributions are:
- We frame instruction generation as natural language program synthesis, formulate it as a black-box optimization problem guided by LLMs, and propose both a naive and an iterative Monte Carlo search methods to approximate the solution.
- Our proposed method, APE, achieves human-level performance on zero-shot learning with model-generated instructions on 19/24 NLP tasks.
- We provide extensive qualitative and quantitative analyses exploring various facets of APE, and demonstrate applications of APE for improving few-shot learning and steering LLMs toward desired behaviors such as truthfulness and/or informativeness.
References
;
| Author | volume | Date Value | title | type | journal | titleUrl | doi | note | year | |
|---|---|---|---|---|---|---|---|---|---|---|
| 2022 LargeLanguageModelsAreHumanLeve | Jimmy Ba Yongchao Zhou Andrei Ioan Muresanu Ziwen Han Keiran Paster Silviu Pitis Harris Chan | Large Language Models Are Human-level Prompt Engineers | 2022 |