# Are Prompt-based Models Clueless?

arXiv: https://arxiv.org/abs/2205.09295 · HTML: https://mlsanity.com/paper/2205.09295/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 28 references that are in the map.
- First posted on arXiv 19 May 2022.

## Builds on (most cited first, 24 of 24)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding](https://mlsanity.com/paper/1804.07461/) (2018)
- [A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference](https://mlsanity.com/paper/1704.05426/) (2017)
- [Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing](https://mlsanity.com/paper/2107.13586/) (2021)
- [A large annotated corpus for learning natural language inference](https://mlsanity.com/paper/1508.05326/) (2015)
- [SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems](https://mlsanity.com/paper/1905.00537/) (2019)
- [Making Pre-trained Language Models Better Few-shot Learners](https://mlsanity.com/paper/2012.15723/) (2020)
- [Exploiting Cloze Questions for Few Shot Text Classification and Natural Language Inference](https://mlsanity.com/paper/2001.07676/) (2020)
- [Bag of Tricks for Efficient Text Classification](https://mlsanity.com/paper/1607.01759/) (2016)
- [Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inference](https://mlsanity.com/paper/1902.01007/) (2019)
- [Annotation Artifacts in Natural Language Inference Data](https://mlsanity.com/paper/1803.02324/) (2018)
- [It's Not Just Size That Matters: Small Language Models Are Also Few-Shot Learners](https://mlsanity.com/paper/2009.07118/) (2020)
- [Attention is not not Explanation](https://mlsanity.com/paper/1908.04626/) (2019)
- [Hypothesis Only Baselines in Natural Language Inference](https://mlsanity.com/paper/1805.01042/) (2018)
- [Analyzing the Structure of Attention in a Transformer Language Model](https://mlsanity.com/paper/1906.04284/) (2019)
- [Probing Neural Network Comprehension of Natural Language Arguments](https://mlsanity.com/paper/1907.07355/) (2019)
- [How Many Data Points is a Prompt Worth?](https://mlsanity.com/paper/2103.08493/) (2021)
- [Adversarial Filters of Dataset Biases](https://mlsanity.com/paper/2002.04108/) (2020)
- [Towards Debiasing Fact Verification Models](https://mlsanity.com/paper/1908.05267/) (2019)
- [What Makes Reading Comprehension Questions Easier?](https://mlsanity.com/paper/1808.09384/) (2018)
- [When Choosing Plausible Alternatives, Clever Hans can be Clever](https://mlsanity.com/paper/1911.00225/) (2019)
- [How Reasonable are Common-Sense Reasoning Tasks: A Case-Study on the Winograd Schema Challenge and SWAG](https://mlsanity.com/paper/1811.01778/) (2018)

## Built on by (most cited first, 11 of 11)

- [State-of-the-art generalisation research in NLP: A taxonomy and review](https://mlsanity.com/paper/2210.03050/) (2022)
- [Revisiting Out-of-distribution Robustness in NLP: Benchmark, Analysis, and LLMs Evaluations](https://mlsanity.com/paper/2306.04618/) (2023)
- [Language Model Behavior: A Comprehensive Survey](https://mlsanity.com/paper/2303.11504/) (2023)
- [Language Model Analysis for Ontology Subsumption Inference](https://mlsanity.com/paper/2302.06761/) (2023)
- [Evaluating the Robustness of Discrete Prompts](https://mlsanity.com/paper/2302.05619/) (2023)
- [Leaving the barn door open for Clever Hans: Simple features predict LLM benchmark answers](https://mlsanity.com/paper/2410.11672/) (2024)
- [Adversarial Robustness of Prompt-based Few-Shot Learning for Natural Language Understanding](https://mlsanity.com/paper/2306.11066/) (2023)
- [Stabilized In-Context Learning with Pre-trained Language Models for Few Shot Dialogue State Tracking](https://mlsanity.com/paper/2302.05932/) (2023)
- [Continuous Prompt Tuning Based Textual Entailment Model for E-commerce Entity Typing](https://mlsanity.com/paper/2211.02483/) (2022)
- [Explanation Regeneration via Information Bottleneck](https://mlsanity.com/paper/2212.09603/) (2022)
- [Helping Language Models Learn More: Multi-dimensional Task Prompt for Few-shot Tuning](https://mlsanity.com/paper/2312.08027/) (2023)

## Abstract (arXiv)

Finetuning large pre-trained language models with a task-specific head has advanced the state-of-the-art on many natural language understanding benchmarks. However, models with a task-specific head require a lot of training data, making them susceptible to learning and exploiting dataset-specific superficial cues that do not generalize to other datasets. Prompting has reduced the data requirement by reusing the language model head and formatting the task input to match the pre-training objective. Therefore, it is expected that few-shot prompt-based models do not exploit superficial cues. This paper presents an empirical examination of whether few-shot prompt-based models also exploit superficial cues. Analyzing few-shot prompt-based models on MNLI, SNLI, HANS, and COPA has revealed that prompt-based models also exploit superficial cues. While the models perform well on instances with superficial cues, they often underperform or only marginally outperform random accuracy on instances without superficial cues.