Do Prompt-Based Models Really Understand the Meaning of Their Prompts?

Citations Over TimeTop 1% of 2022 papers

Abstract

Recently, a boom of papers has shown extraordinary progress in zero-shot and few-shot learning with various prompt-based models. It is commonly argued that prompts help models to learn faster in the same way that humans learn faster when provided with task instructions expressed in natural language. In this study, we experiment with over 30 prompt templates manually written for natural language inference (NLI). We find that models can learn just as fast with many prompts that are intentionally irrelevant or even pathologically misleading as they do with instructively "good" prompts. Further, such patterns hold even for models as large as 175 billion parameters That is, instruction-tuned models often produce good predictions with irrelevant and misleading prompts even at zero shots. In sum, notwithstanding prompt-based models' impressive improvement, we find evidence of serious limitations that question the degree to which such improvement is derived from models understanding task instructions in ways analogous to humans' use of task instructions. * Unabridged version available on arXiv. Code, interactive figures, and statistical test results available at https://github. com/awebson/prompt_semantics arbitrary dimensions of a one-hot vector. In contrast, suppose a human is given a prompt such as: Given that " Given that " Given that " Given that " Given that " Given that " Given that " Given that " Given that " Given that " Given that " Given that " Given that " Given that " Given that " Given that " Given that "no weapons of mass destruction found in Iraq yet.", is it definitely correct that " ", is it definitely correct that " ", is it definitely correct that " ", is it definitely correct that " ", is it definitely correct that " ", is it definitely correct that " ", is it definitely correct that " ", is it definitely correct that " ", is it definitely correct that " ", is it definitely correct that " ", is it definitely correct that " ", is it definitely correct that " ", is it definitely correct that " ", is it definitely correct that " ", is it definitely correct that " ", is it definitely correct that " ", is it definitely correct that "weapons of mass destruction found in Iraq."? "? "? "? "? "? "? "? "? "? "? "? "? "? "? "? "? 1 Then it would be no surprise that they are able to perform the task more accurately and without needing many examples to figure out what the task is.

Related Papers

• → Text to Code Conversion Using Deep Learning for NLP(2020)3 cited
• → Automatic Keyword Extraction from Single-Sentence Natural Language Queries(2012)3 cited
• → Automatic Labeling of Semantic Roles with a Dependency Parser in Hungarian Economic Texts(2015)1 cited
• → A Hybrid Approach to Parsing Natural Languages(2016)1 cited
• → A Survey on Large Scale Corpora and Emotion Corpora(2014)