2022

HELP ME THINK: A Simple Prompting Strategy for Non-experts to Create Customized Content with Models

Mishra, Swaroop, Nouri, Elnaz

Understand

Controlling the text generated by language models and customizing the content has been a long-standing challenge.

Existing prompting techniques proposed in pursuit of providing control are task-specific and lack generality; this provides overwhelming choices for non-expert users to find a suitable method for their task.
The effort associated with those techniques, such as in writing examples, explanations, instructions, etc.
further limits their adoption among non-expert users.

Built on

Language models are few-shot learners
Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, et al. 2020 · 1901
Earlier work this paper cites.
Text modular networks: Learning to decompose tasks in the language of existing models
Original
Tushar Khot, Daniel Khashabi, Kyle Richardson, Peter Clark, and Ashish Sabharwal. 2020 · 2009
Earlier work this paper cites.
The turking test: Can language models understand instructions?
Original
Avia Efrat and Omer Levy. 2020 · 2010
Earlier work this paper cites.
Learning from task descriptions
Original
Orion Weller, Nicholas Lourie, Matt Gardner, and Matthew E Peters. 2020 · 2011
Earlier work this paper cites.
An imitation game for learning semantic parsers from user interaction
Ziyu Yao, Yiqi Tang, Wen-tau Yih, Huan Sun, and Yu Su. 2020 · 2020
Earlier work this paper cites.
Adaprompt: Adaptive prompt-based finetuning for relation extraction
Xiang Chen, Xin Xie, Ningyu Zhang, Jiahuan Yan, Shumin Deng, Chuanqi Tan, Fei Huang, Luo Si, and Huajun Chen. 2021 · 2021
Earlier work this paper cites.
How many data points is a prompt worth?
Teven Le Scao and Alexander M Rush. 2021 · 2021
Earlier work this paper cites.
Pre-train, prompt, and predict: A systematic survey of prompting methods in natural language processing
Original
Pengfei Liu, Weizhe Yuan, Jinlan Fu, Zhengbao Jiang, Hiroaki Hayashi, and Graham Neubig. 2021 · 2021
Earlier work this paper cites.
Show your work: Scratchpads for intermediate computation with language models
Original
Maxwell Nye, Anders Johan Andreassen, Guy Gur-Ari, Henryk Michalewski, Jacob Austin, David Bieber, David Dohan, Aitor Lewkowycz, Maarten Bosma, David Luan, et al. 2021 · 2021
Earlier work this paper cites.
A recipe for arbitrary text style transfer with large language models
Original
Emily Reif, Daphne Ippolito, Ann Yuan, Andy Coenen, Chris Callison-Burch, and Jason Wei. 2021 · 2021
Earlier work this paper cites.

Similar

Multitask prompted training enables zero-shot task generalization
Original
Victor Sanh, Albert Webson, Colin Raffel, Stephen H Bach, Lintang Sutawika, Zaid Alyafeai, Antoine Chaffin, Arnaud Stiegler, Teven Le Scao, Arun Raja, et al. 2021 · 2021
Cited alongside, same era.
Finetuned language models are zero-shot learners
Original
Jason Wei, Maarten Bosma, Vincent Y Zhao, Kelvin Guu, Adams Wei Yu, Brian Lester, Nan Du, Andrew M Dai, and Quoc V Le. 2021 · 2021
Cited alongside, same era.
Adapting language models for zero-shot learning by meta-tuning on dataset and prompt collections
Original
Ruiqi Zhong, Kristy Lee, Zheng Zhang, and Dan Klein. 2021 · 2021
Cited alongside, same era.
Do as i can, not as i say: Grounding language in robotic affordances
Original
Michael Ahn, Anthony Brohan, Noah Brown, Yevgen Chebotar, Omar Cortes, Byron David, Chelsea Finn, Keerthana Gopalakrishnan, Karol Hausman, Alex Herzog, et al. 2022 · 2022
Cited alongside, same era.
Palm: Scaling language modeling with pathways
Original
Aakanksha Chowdhery, Sharan Narang, Jacob Devlin, Maarten Bosma, Gaurav Mishra, Adam Roberts, Paul Barham, Hyung Won Chung, Charles Sutton, Sebastian Gehrmann, et al. 2022 · 2022
Cited alongside, same era.
Make-a-scene: Scene-based text-to-image generation with human priors
Original
Oran Gafni, Adam Polyak, Oron Ashual, Shelly Sheynin, Devi Parikh, and Yaniv Taigman. 2022 · 2022
Cited alongside, same era.
Improving zero and few-shot generalization in dialogue through instruction tuning
Original
Prakhar Gupta, Cathy Jiao, Yi-Ting Yeh, Shikib Mehri, Maxine Eskenazi, and Jeffrey P Bigham. 2022 · 2022
Cited alongside, same era.
Less is more: Summary of long instructions is better for program synthesis
Original
Kirby Kuznia, Swaroop Mishra, Mihir Parmar, and Chitta Baral. 2022 · 2022
Cited alongside, same era.
Biotabqa: Instruction learning for biomedical table question answering
Original
Man Luo, Sharad Saxena, Swaroop Mishra, Mihir Parmar, and Chitta Baral. 2022 · 2022
Cited alongside, same era.
Reframing instructional prompts to GPTk’s language
Swaroop Mishra, Daniel Khashabi, Chitta Baral, Yejin Choi, and Hannaneh Hajishirzi. 2022a · 2022
Cited alongside, same era.
Cross-task generalization via natural language crowdsourcing instructions
Swaroop Mishra, Daniel Khashabi, Chitta Baral, and Hannaneh Hajishirzi. 2022b
Cited in the paper.
Instructionner: A multi-task instruction-based generative framework for few-shot ner
Original
Liwen Wang, Rumei Li, Yang Yan, Yuanmeng Yan, Sirui Wang, Wei Wu, and Weiran Xu. 2022a
Cited in the paper.

Then

Training language models to follow instructions with human feedback
Long Ouyang, Jeff Wu, Xu Jiang, Diogo Almeida, Carroll L Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, et al. 2022 · 2022
Closest in time.
In-boxbart: Get instructions into biomedical multi-task learning
Original
Mihir Parmar, Swaroop Mishra, Mirali Purohit, Man Luo, M Hassan Murad, and Chitta Baral. 2022 · 2022
Closest in time.
Is a question decomposition unit all we need?
Original
Pruthvi Patel, Swaroop Mishra, Mihir Parmar, and Chitta Baral. 2022 · 2022
Closest in time.
Finding and Fixing Undesirable Behaviors in Pretrained Language Models
Ethan Perez. 2022 · 2022
Closest in time.
How many data samples is an additional instruction worth?
Original
Ravsehaj Singh Puri, Swaroop Mishra, Mihir Parmar, and Chitta Baral. 2022 · 2022
Closest in time.
Chain of thought prompting elicits reasoning in large language models
Original
Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Ed Chi, Quoc Le, and Denny Zhou. 2022 · 2022
Closest in time.
Compositional task-oriented parsing as abstractive question answering
Original
Wenting Zhao, Konstantine Arkoudas, Weiqi Sun, and Claire Cardie. 2022 · 2022
Closest in time.
Active programming by example with a natural language prior
Ruiqi Zhong, Charlie Snell, Dan Klein, and Jason Eisner. 2022 · 2022
Closest in time.
Least-to-most prompting enables complex reasoning in large language models
Original
Denny Zhou, Nathanael Schärli, Le Hou, Jason Wei, Nathan Scales, Xuezhi Wang, Dale Schuurmans, Olivier Bousquet, Quoc Le, and Ed Chi. 2022 · 2022
Closest in time.
Instructabsa: Instruction learning for aspect based sentiment analysis
Original
Kevin Scaria, Himanshu Gupta, Saurabh Arjun Sawant, Swaroop Mishra, and Chitta Baral. 2023 · 2023
Closest in time.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…

Reading the bibliography…