# PSP: Pre-trained Soft Prompts for Few-Shot Abstractive Summarization

arXiv: https://arxiv.org/abs/2204.04413 · HTML: https://mlsanity.com/paper/2204.04413/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 40 references that are in the map.
- First posted on arXiv 9 Apr 2022.

## Builds on (most cited first, 26 of 26)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (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)
- [Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarization](https://mlsanity.com/paper/1808.08745/) (2018)
- [Get To The Point: Summarization with Pointer-Generator Networks](https://mlsanity.com/paper/1704.04368/) (2017)
- [Making Pre-trained Language Models Better Few-shot Learners](https://mlsanity.com/paper/2012.15723/) (2020)
- [PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization](https://mlsanity.com/paper/1912.08777/) (2019)
- [Teaching Machines to Read and Comprehend](https://mlsanity.com/paper/1506.03340/) (2015)
- [Multilingual Denoising Pre-training for Neural Machine Translation](https://mlsanity.com/paper/2001.08210/) (2020)
- [How Can We Know What Language Models Know?](https://mlsanity.com/paper/1911.12543/) (2019)
- [GPT Understands, Too](https://mlsanity.com/paper/2103.10385/) (2021)
- [Text Summarization with Pretrained Encoders](https://mlsanity.com/paper/1908.08345/) (2019)
- [True Few-Shot Learning with Language Models](https://mlsanity.com/paper/2105.11447/) (2021)
- [PPT: Pre-trained Prompt Tuning for Few-shot Learning](https://mlsanity.com/paper/2109.04332/) (2021)
- [Cutting Down on Prompts and Parameters: Simple Few-Shot Learning with Language Models](https://mlsanity.com/paper/2106.13353/) (2021)
- [A Good Prompt Is Worth Millions of Parameters: Low-resource Prompt-based Learning for Vision-Language Models](https://mlsanity.com/paper/2110.08484/) (2021)
- [Best-Worst Scaling More Reliable than Rating Scales: A Case Study on Sentiment Intensity Annotation](https://mlsanity.com/paper/1712.01765/) (2017)
- [Improving Zero and Few-Shot Abstractive Summarization with Intermediate Fine-tuning and Data Augmentation](https://mlsanity.com/paper/2010.12836/) (2020)
- [AdaptSum: Towards Low-Resource Domain Adaptation for Abstractive Summarization](https://mlsanity.com/paper/2103.11332/) (2021)
- [SelfORE: Self-supervised Relational Feature Learning for Open Relation Extraction](https://mlsanity.com/paper/2004.02438/) (2020)
- [Gradient Imitation Reinforcement Learning for Low Resource Relation Extraction](https://mlsanity.com/paper/2109.06415/) (2021)
- [TED: A Pretrained Unsupervised Summarization Model with Theme Modeling and Denoising](https://mlsanity.com/paper/2001.00725/) (2020)
- [Cross-Lingual Abstractive Summarization with Limited Parallel Resources](https://mlsanity.com/paper/2105.13648/) (2021)
- [Concept Pointer Network for Abstractive Summarization](https://mlsanity.com/paper/1910.08486/) (2019)

## Built on by (most cited first, 14 of 14)

- [Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning](https://mlsanity.com/paper/2205.05638/) (2022)
- [ChatGPT vs Human-authored Text: Insights into Controllable Text Summarization and Sentence Style Transfer](https://mlsanity.com/paper/2306.07799/) (2023)
- [InfoPrompt: Information-Theoretic Soft Prompt Tuning for Natural Language Understanding](https://mlsanity.com/paper/2306.04933/) (2023)
- [Learning Instructions with Unlabeled Data for Zero-Shot Cross-Task Generalization](https://mlsanity.com/paper/2210.09175/) (2022)
- [UniSumm and SummZoo: Unified Model and Diverse Benchmark for Few-Shot Summarization](https://mlsanity.com/paper/2211.09783/) (2022)
- [Query Refinement Prompts for Closed-Book Long-Form Question Answering](https://mlsanity.com/paper/2210.17525/) (2022)
- [Towards Summary Candidates Fusion](https://mlsanity.com/paper/2210.08779/) (2022)
- [PromptSum: Parameter-Efficient Controllable Abstractive Summarization](https://mlsanity.com/paper/2308.03117/) (2023)
- [Few-Shot Dialogue Summarization via Skeleton-Assisted Prompt Transfer in Prompt Tuning](https://mlsanity.com/paper/2305.12077/) (2023)
- [Injecting knowledge into language generation: a case study in auto-charting after-visit care instructions from medical dialogue](https://mlsanity.com/paper/2306.03652/) (2023)
- [Scene Graph Modification as Incremental Structure Expanding](https://mlsanity.com/paper/2209.09093/) (2022)
- [PROM: A Phrase-level Copying Mechanism with Pre-training for Abstractive Summarization](https://mlsanity.com/paper/2305.06647/) (2023)
- [Sample Efficient Multimodal Semantic Augmentation for Incremental Summarization](https://mlsanity.com/paper/2303.04361/) (2023)
- [Recent Trends in Unsupervised Summarization](https://mlsanity.com/paper/2305.11231/) (2023)

## Abstract (arXiv)

Few-shot abstractive summarization has become a challenging task in natural language generation. To support it, we designed a novel soft prompts architecture coupled with a prompt pre-training plus fine-tuning paradigm that is effective and tunes only extremely light parameters. The soft prompts include continuous input embeddings across an encoder and a decoder to fit the structure of the generation models. Importantly, a novel inner-prompt placed in the text is introduced to capture document-level information. The aim is to devote attention to understanding the document that better prompts the model to generate document-related content. The first step in the summarization procedure is to conduct prompt pre-training with self-supervised pseudo-data. This teaches the model basic summarizing capabilities. The model is then fine-tuned with few-shot examples. Experimental results on the CNN/DailyMail and XSum datasets show that our method, with only 0.1% of the parameters, outperforms full-model tuning where all model parameters are tuned. It also surpasses Prompt Tuning by a large margin and delivers competitive results against Prefix-Tuning with 3% of the parameters.