mlsanityData to 7 Oct 2026

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

arXiv 2212.00616 ↗First posted 1 Dec 2022cs.CLcited by 6

Not on the map. Why?

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.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 29 of its 36 references that are in the map. First posted on arXiv 1 Dec 2022.

Builds on

29 of 36 references.

References · 29

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2020Language Models are Few-Shot Learnerscited by 32,199
  4. 2022Training language models to follow instructions with human feedbackcited by 15,712
  5. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  6. 2021Prefix-Tuning: Optimizing Continuous Prompts for Generationcited by 3,878
  7. 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,769
  8. 2022OPT: Open Pre-trained Transformer Language Modelscited by 3,464
  9. 2019The Curious Case of Neural Text Degenerationcited by 2,881
  10. 2022An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversioncited by 2,231
  11. 2019ZeRO: Memory Optimizations Toward Training Trillion Parameter Modelscited by 1,278
  12. 2020Making Pre-trained Language Models Better Few-shot Learnerscited by 1,255
17 more
  1. 2019How Can We Know What Language Models Know?cited by 953
  2. 2020Exploiting Cloze Questions for Few Shot Text Classification and Natural Language Inferencecited by 934
  3. 2021GPT Understands, Toocited by 715
  4. 2021Learning How to Ask: Querying LMs with Mixtures of Soft Promptscited by 376
  5. 2021PTR: Prompt Tuning with Rules for Text Classificationcited by 238
  6. 2021SPoT: Better Frozen Model Adaptation through Soft Prompt Transfercited by 235
  7. 2018Dear Sir or Madam, May I introduce the GYAFC Dataset: Corpus, Benchmarks and Metrics for Formality Style Transfercited by 209
  8. 2019Commonsense Knowledge Mining from Pretrained Modelscited by 189
  9. 2021Knowledgeable Prompt-tuning: Incorporating Knowledge into Prompt Verbalizer for Text Classificationcited by 183
  10. 2021Challenges in Detoxifying Language Modelscited by 169
  11. 2021On Transferability of Prompt Tuning for Natural Language Processingcited by 74
  12. 2021PADA: Example-based Prompt Learning for on-the-fly Adaptation to Unseen Domainscited by 61
  13. 2020Parallel Data Augmentation for Formality Style Transfercited by 39
  14. 2022Text Revision by On-the-Fly Representation Optimizationcited by 17
  15. 2019Formality Style Transfer with Hybrid Textual Annotationscited by 16
  16. 2022Reducing Retraining by Recycling Parameter-Efficient Promptscited by 11
  17. 2022Are Sample-Efficient NLP Models More Robust?cited by 5

Built on by

Cited by year

Citing papers per year: 2023: 2; 2024: 4.

6 papers.

  1. 2023In-context Autoencoder for Context Compression in a Large Language Modelcited by 190
  2. 2024Prompt Compression for Large Language Models: A Surveycited by 65
  3. 2024Efficient Prompting Methods for Large Language Models: A Surveycited by 46
  4. 2024Position IDs Matter: An Enhanced Position Layout for Efficient Context Compression in Large Language Modelscited by 9
  5. 2024AdaCoder: Adaptive Prompt Compression for Programmatic Visual Question Answeringcited by 1
  6. 2023ELODIN: Naming Concepts in Embedding Spacescited by 0