Reframing Instructional Prompts to GPTk's Language
What kinds of instructional prompts are easier to follow for Language Models (LMs)? We study this question by conducting extensive empirical analysis that shed light on important features of successful instructional prompts. We propose several reframing techniques for model designers to manually create more effective prompts. Some examples include decomposing a complex task instruction into multiple simpler tasks or itemizing instructions into sequential steps. Our experiments compare the zero-shot and few-shot performance of LMs prompted with reframed instructions on 12 NLP tasks across 6 categories. Compared with original instructions, our reframed instructions lead to significant improvements across LMs with different sizes, underscoring the cross-model generality of these guidelines. For example, the same reframed prompts boost few-shot performance of GPT3-series and GPT2-series by 12.5% and 6.7% respectively averaged over all tasks. Furthermore, reframed instructions reduce the number of examples required to prompt LMs in the few-shot setting. We hope these empirically-driven techniques will pave the way for more effective ways to prompt LMs in the future.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Reframing Instructional Prompts to GPTk's Language
What kinds of instructional prompts are easier to follow for Language Models (LMs)? We study this question by conducting extensive empirical analysis that shed light on important features of successful instructional prom…
Few-Shot LearningQuestion GenerationZero-Shot LearningReframing Instructional Prompts to GPTk’s Language
What kinds of instructional prompts are easier to follow for Language Models (LMs)? We study this question by conducting extensive empirical analysis that shed light on important features of successful instructional prom…
GPTKB 2.0: Direct Construction of Disambiguated Knowledge Bases from Large Language Models
Automated Knowledge Base Construction (AKBC) is a core NLP task, and recent work proposes generating knowledge bases directly from large language models (LLMs), treating the model itself as the knowledge source. However,…
MOGPTK: The Multi-Output Gaussian Process Toolkit
We present MOGPTK, a Python package for multi-channel data modelling using Gaussian processes (GP). The aim of this toolkit is to make multi-output GP (MOGP) models accessible to researchers, data scientists, and practit…
Gaussian ProcessesGPUImputationGPTKB v1.5: A Massive Knowledge Base for Exploring Factual LLM Knowledge
Language models are powerful artifacts, yet their factual knowledge is still poorly understood, and inaccessible to ad-hoc browsing and scalable statistical analysis. This demonstration introduces GPTKB v1.5, a densely i…