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

arXiv: https://arxiv.org/abs/2109.01247 · HTML: https://mlsanity.com/paper/2109.01247/

## Key facts

- Cited by 326 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 75 references that are in the map.
- First posted on arXiv 2 Sep 2021.

## Builds on (most cited first, 30 of 30)

- [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)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [ALBERT: A Lite BERT for Self-supervised Learning of Language Representations](https://mlsanity.com/paper/1909.11942/) (2019)
- [A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference](https://mlsanity.com/paper/1704.05426/) (2017)
- [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)
- [How Can We Know What Language Models Know?](https://mlsanity.com/paper/1911.12543/) (2019)
- [Exploiting Cloze Questions for Few Shot Text Classification and Natural Language Inference](https://mlsanity.com/paper/2001.07676/) (2020)
- [Adafactor: Adaptive Learning Rates with Sublinear Memory Cost](https://mlsanity.com/paper/1804.04235/) (2018)
- [Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inference](https://mlsanity.com/paper/1902.01007/) (2019)
- [Adversarial NLI: A New Benchmark for Natural Language Understanding](https://mlsanity.com/paper/1910.14599/) (2019)
- [It's Not Just Size That Matters: Small Language Models Are Also Few-Shot Learners](https://mlsanity.com/paper/2009.07118/) (2020)
- [Learning How to Ask: Querying LMs with Mixtures of Soft Prompts](https://mlsanity.com/paper/2104.06599/) (2021)
- [What BERT is not: Lessons from a new suite of psycholinguistic diagnostics for language models](https://mlsanity.com/paper/1907.13528/) (2019)
- [How Many Data Points is a Prompt Worth?](https://mlsanity.com/paper/2103.08493/) (2021)
- [Cutting Down on Prompts and Parameters: Simple Few-Shot Learning with Language Models](https://mlsanity.com/paper/2106.13353/) (2021)
- [Knowledgeable or Educated Guess? Revisiting Language Models as Knowledge Bases](https://mlsanity.com/paper/2106.09231/) (2021)
- [Improving and Simplifying Pattern Exploiting Training](https://mlsanity.com/paper/2103.11955/) (2021)
- [The Turking Test: Can Language Models Understand Instructions?](https://mlsanity.com/paper/2010.11982/) (2020)
- [Learning from Task Descriptions](https://mlsanity.com/paper/2011.08115/) (2020)
- [Out of Order: How Important Is The Sequential Order of Words in a Sentence in Natural Language Understanding Tasks?](https://mlsanity.com/paper/2012.15180/) (2020)
- [UnNatural Language Inference](https://mlsanity.com/paper/2101.00010/) (2020)
- [FLEX: Unifying Evaluation for Few-Shot NLP](https://mlsanity.com/paper/2107.07170/) (2021)
- [What Context Features Can Transformer Language Models Use?](https://mlsanity.com/paper/2106.08367/) (2021)
- [BERT & Family Eat Word Salad: Experiments with Text Understanding](https://mlsanity.com/paper/2101.03453/) (2021)

## Built on by (most cited first, 30 of 326)

- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them](https://mlsanity.com/paper/2210.09261/) (2022)
- [Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?](https://mlsanity.com/paper/2202.12837/) (2022)
- [Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting](https://mlsanity.com/paper/2305.04388/) (2023)
- [Large Language Models Are Human-Level Prompt Engineers](https://mlsanity.com/paper/2211.01910/) (2022)
- [Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning](https://mlsanity.com/paper/2205.05638/) (2022)
- [Large Language Models Can Be Easily Distracted by Irrelevant Context](https://mlsanity.com/paper/2302.00093/) (2023)
- [Automatic Chain of Thought Prompting in Large Language Models](https://mlsanity.com/paper/2210.03493/) (2022)
- [A Comprehensive Overview of Large Language Models](https://mlsanity.com/paper/2307.06435/) (2023)
- [Is ChatGPT a General-Purpose Natural Language Processing Task Solver?](https://mlsanity.com/paper/2302.06476/) (2023)
- [Recent Advances in Natural Language Processing via Large Pre-Trained Language Models: A Survey](https://mlsanity.com/paper/2111.01243/) (2021)
- [Harnessing the Power of LLMs in Practice: A Survey on ChatGPT and Beyond](https://mlsanity.com/paper/2304.13712/) (2023)
- [Using cognitive psychology to understand GPT-3](https://mlsanity.com/paper/2206.14576/) (2022)
- [Larger language models do in-context learning differently](https://mlsanity.com/paper/2303.03846/) (2023)
- [RLPrompt: Optimizing Discrete Text Prompts with Reinforcement Learning](https://mlsanity.com/paper/2205.12548/) (2022)
- [Data Distributional Properties Drive Emergent In-Context Learning in Transformers](https://mlsanity.com/paper/2205.05055/) (2022)
- [PromptSource: An Integrated Development Environment and Repository for Natural Language Prompts](https://mlsanity.com/paper/2202.01279/) (2022)
- [TabLLM: Few-shot Classification of Tabular Data with Large Language Models](https://mlsanity.com/paper/2210.10723/) (2022)
- [Reasoning with Language Model Prompting: A Survey](https://mlsanity.com/paper/2212.09597/) (2022)
- [Can language models learn from explanations in context?](https://mlsanity.com/paper/2204.02329/) (2022)
- [Towards Understanding Chain-of-Thought Prompting: An Empirical Study of What Matters](https://mlsanity.com/paper/2212.10001/) (2022)
- [Evaluating the Moral Beliefs Encoded in LLMs](https://mlsanity.com/paper/2307.14324/) (2023)
- [Unlearn What You Want to Forget: Efficient Unlearning for LLMs](https://mlsanity.com/paper/2310.20150/) (2023)
- [Chain-of-Thought Reasoning Without Prompting](https://mlsanity.com/paper/2402.10200/) (2024)
- [CREPE: Can Vision-Language Foundation Models Reason Compositionally?](https://mlsanity.com/paper/2212.07796/) (2022)
- [Do LLMs exhibit human-like response biases? A case study in survey design](https://mlsanity.com/paper/2311.04076/) (2023)
- [Lessons from the Trenches on Reproducible Evaluation of Language Models](https://mlsanity.com/paper/2405.14782/) (2024)
- [Can Foundation Models Wrangle Your Data?](https://mlsanity.com/paper/2205.09911/) (2022)
- [Language models show human-like content effects on reasoning tasks](https://mlsanity.com/paper/2207.07051/) (2022)

## Abstract (arXiv)

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 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., 2022). 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.