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

Anonymous

Paper Link: https://openreview.net/forum?id=05iM3QT1FDE

Paper Type: Long paper (up to eight pages of content + unlimited references and appendices)

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 prompts 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 (Brown et al., 2020) as well as the recently proposed instruction-tuned models which are trained on hundreds of prompts (Sanh et al., 2021). 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.

Presentation Mode: This paper will be presented in person in Seattle

Copyright Consent Signature (type Name Or NA If Not Transferrable): Albert Webson

Copyright Consent Name And Address: Brown University, 115 Waterman St, Providence, RI, 02912