# Extensible Prompts for Language Models on Zero-shot Language Style Customization

arXiv: https://arxiv.org/abs/2212.00616 · HTML: https://mlsanity.com/paper/2212.00616/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 36 references that are in the map.
- First posted on arXiv 1 Dec 2022.

## Builds on (most cited first, 29 of 29)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [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)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion](https://mlsanity.com/paper/2208.01618/) (2022)
- [ZeRO: Memory Optimizations Toward Training Trillion Parameter Models](https://mlsanity.com/paper/1910.02054/) (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)
- [GPT Understands, Too](https://mlsanity.com/paper/2103.10385/) (2021)
- [Learning How to Ask: Querying LMs with Mixtures of Soft Prompts](https://mlsanity.com/paper/2104.06599/) (2021)
- [PTR: Prompt Tuning with Rules for Text Classification](https://mlsanity.com/paper/2105.11259/) (2021)
- [SPoT: Better Frozen Model Adaptation through Soft Prompt Transfer](https://mlsanity.com/paper/2110.07904/) (2021)
- [Dear Sir or Madam, May I introduce the GYAFC Dataset: Corpus, Benchmarks and Metrics for Formality Style Transfer](https://mlsanity.com/paper/1803.06535/) (2018)
- [Commonsense Knowledge Mining from Pretrained Models](https://mlsanity.com/paper/1909.00505/) (2019)
- [Knowledgeable Prompt-tuning: Incorporating Knowledge into Prompt Verbalizer for Text Classification](https://mlsanity.com/paper/2108.02035/) (2021)
- [Challenges in Detoxifying Language Models](https://mlsanity.com/paper/2109.07445/) (2021)
- [On Transferability of Prompt Tuning for Natural Language Processing](https://mlsanity.com/paper/2111.06719/) (2021)
- [PADA: Example-based Prompt Learning for on-the-fly Adaptation to Unseen Domains](https://mlsanity.com/paper/2102.12206/) (2021)
- [Parallel Data Augmentation for Formality Style Transfer](https://mlsanity.com/paper/2005.07522/) (2020)
- [Text Revision by On-the-Fly Representation Optimization](https://mlsanity.com/paper/2204.07359/) (2022)
- [Formality Style Transfer with Hybrid Textual Annotations](https://mlsanity.com/paper/1903.06353/) (2019)
- [Reducing Retraining by Recycling Parameter-Efficient Prompts](https://mlsanity.com/paper/2208.05577/) (2022)
- [Are Sample-Efficient NLP Models More Robust?](https://mlsanity.com/paper/2210.06456/) (2022)

## Built on by (most cited first, 6 of 6)

- [In-context Autoencoder for Context Compression in a Large Language Model](https://mlsanity.com/paper/2307.06945/) (2023)
- [Prompt Compression for Large Language Models: A Survey](https://mlsanity.com/paper/2410.12388/) (2024)
- [Efficient Prompting Methods for Large Language Models: A Survey](https://mlsanity.com/paper/2404.01077/) (2024)
- [Position IDs Matter: An Enhanced Position Layout for Efficient Context Compression in Large Language Models](https://mlsanity.com/paper/2409.14364/) (2024)
- [AdaCoder: Adaptive Prompt Compression for Programmatic Visual Question Answering](https://mlsanity.com/paper/2407.19410/) (2024)
- [ELODIN: Naming Concepts in Embedding Spaces](https://mlsanity.com/paper/2303.04001/) (2023)

## Abstract (arXiv)

We propose eXtensible Prompt (X-Prompt) for prompting a large language model (LLM) beyond natural language (NL). X-Prompt instructs an LLM with not only NL but also an extensible vocabulary of imaginary words. Registering new imaginary words allows us to instruct the LLM to comprehend concepts that are difficult to describe with NL words, thereby making a prompt more descriptive. Also, these imaginary words are designed to be out-of-distribution (OOD) robust so that they can be (re)used like NL words in various prompts, distinguishing X-Prompt from soft prompt that is for fitting in-distribution data. We propose context-augmented learning (CAL) to learn imaginary words for general usability, enabling them to work properly in OOD (unseen) prompts. We experiment X-Prompt for zero-shot language style customization as a case study. The promising results of X-Prompt demonstrate its potential to facilitate advanced interaction beyond the natural language interface, bridging the communication gap between humans and LLMs.