Shepherd Pre-trained Language Models to Develop a Train of Thought: An Iterative Prompting Approach

By Boshi Wang, Xiang Deng, Huan Sun. 2022

9 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Prompting & Reasoning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Mohit Bansal
2. Luke S. Zettlemoyer
3. Noah A. Smith
4. Quoc V. Le
5. Graham Neubig
6. Hannaneh Hajishirzi
7. Percy Liang
8. Yejin Choi

In Computer Vision and Pattern Recognition

1. Mohit Bansal
2. Noah A. Smith
3. Luc Van Gool
4. Dacheng Tao
5. Quoc V. Le
6. Jianfeng Gao
7. Trevor Darrell
8. Luke S. Zettlemoyer

In Prompting & Reasoning

1. Denny Zhou
2. Jason Wei
3. Xuezhi Wang
4. Ed H. Chi
5. Quoc V. Le
6. Nathanael Scharli
7. Wenhu Chen
8. Nathan Scales

Citations in the corpus

• Least-to-Most Prompting Enables Complex Reasoning in Large Language Models (2022, methodology): “In this respect, it shares the same spirit as the methods in (Graves, 2016; Dehghani et al., 2019; Dong et al., 2019; Schwarzschild et al., 2021; Wang et al., 2021; Wei et al., 2022; Wang et al., 2022).”
• Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning (2022, methodology): “Prompt tuning has been applied to various applications for NLP including continual learning [59], model robustness [60, 61], summarization [62], machine translation [63], co-training [64], probing language models [65, 65], inverse prompting [66], and transfer learning [67].”
• Measuring and Narrowing the Compositionality Gap in Language Models (2022, methodology): “2022) trained supervised models to decompose compositional questions into sub-questions.”
• Reasoning with Language Model Prompting: A Survey (2022, unknown): “Multi-Stage IterPrompt (Wang et al., 2022b), SI (Creswell et al.”
• Decomposition Enhances Reasoning via Self-Evaluation Guided Decoding (2023, unknown): “To mitigate this issue, Wang et al. (2022b) conduct majority voting to approximate the expectation via sampling and aggregating multiple reasoning chains.”