# Zero-shot Approach to Overcome Perturbation Sensitivity of Prompts

arXiv: https://arxiv.org/abs/2305.15689 · HTML: https://mlsanity.com/paper/2305.15689/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 31 references that are in the map.
- First posted on arXiv 25 May 2023.

## Builds on (most cited first, 14 of 14)

- [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)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [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)
- [Factual Probing Is [MASK]: Learning vs. Learning to Recall](https://mlsanity.com/paper/2104.05240/) (2021)
- [PPT: Pre-trained Prompt Tuning for Few-shot Learning](https://mlsanity.com/paper/2109.04332/) (2021)
- [Reframing Instructional Prompts to GPTk's Language](https://mlsanity.com/paper/2109.07830/) (2021)
- [Adapting Language Models for Zero-shot Learning by Meta-tuning on Dataset and Prompt Collections](https://mlsanity.com/paper/2104.04670/) (2021)
- [Discrete and Soft Prompting for Multilingual Models](https://mlsanity.com/paper/2109.03630/) (2021)
- [Towards Unified Prompt Tuning for Few-shot Text Classification](https://mlsanity.com/paper/2205.05313/) (2022)

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

- [Leak, Cheat, Repeat: Data Contamination and Evaluation Malpractices in Closed-Source LLMs](https://mlsanity.com/paper/2402.03927/) (2024)
- [Open (Clinical) LLMs are Sensitive to Instruction Phrasings](https://mlsanity.com/paper/2407.09429/) (2024)
- ["Well, Keep Thinking": Enhancing LLM Reasoning with Adaptive Injection Decoding](https://mlsanity.com/paper/2503.10167/) (2025)
- [The Mystery of the Pathological Path-star Task for Language Models](https://mlsanity.com/paper/2410.13779/) (2024)
- [From Form(s) to Meaning: Probing the Semantic Depths of Language Models Using Multisense Consistency](https://mlsanity.com/paper/2404.12145/) (2024)
- [Making Large Language Models Better Knowledge Miners for Online Marketing with Progressive Prompting Augmentation](https://mlsanity.com/paper/2312.05276/) (2023)
- [Native Design Bias: Studying the Impact of English Nativeness on Language Model Performance](https://mlsanity.com/paper/2406.17385/) (2024)
- [Language Models, Graph Searching, and Supervision Adulteration: When More Supervision is Less and How to Make More More](https://mlsanity.com/paper/2503.10542/) (2025)
- [PromptSuite: A Task-Agnostic Framework for Multi-Prompt Generation](https://mlsanity.com/paper/2507.14913/) (2025)
- [Revisiting Prompt Sensitivity in Large Language Models for Text Classification: The Role of Prompt Underspecification](https://mlsanity.com/paper/2602.04297/) (2026)
- [Modeling Data Diversity for Joint Instance and Verbalizer Selection in Cold-Start Scenarios](https://mlsanity.com/paper/2507.00330/) (2025)

## Abstract (arXiv)

Recent studies have demonstrated that natural-language prompts can help to leverage the knowledge learned by pre-trained language models for the binary sentence-level sentiment classification task. Specifically, these methods utilize few-shot learning settings to fine-tune the sentiment classification model using manual or automatically generated prompts. However, the performance of these methods is sensitive to the perturbations of the utilized prompts. Furthermore, these methods depend on a few labeled instances for automatic prompt generation and prompt ranking. This study aims to find high-quality prompts for the given task in a zero-shot setting. Given a base prompt, our proposed approach automatically generates multiple prompts similar to the base prompt employing positional, reasoning, and paraphrasing techniques and then ranks the prompts using a novel metric. We empirically demonstrate that the top-ranked prompts are high-quality and significantly outperform the base prompt and the prompts generated using few-shot learning for the binary sentence-level sentiment classification task.