Fetching the paper…

Reading the bibliography…

2024

Revisiting OPRO: The Limitations of Small-Scale LLMs as Optimizers

Zhang, Tuo, Yuan, Jinyue, Avestimehr, Salman

Original
PDF
Post on X

Understand

Numerous recent works aim to enhance the efficacy of Large Language Models (LLMs) through strategic prompting.

In particular, the Optimization by PROmpting (OPRO) approach provides state-of-the-art performance by leveraging LLMs as optimizers where the optimization task is to find instructions that maximize the task accuracy.
In this paper, we revisit OPRO for automated prompting with relatively small-scale LLMs, such as LLaMa-2 family and Mistral 7B.
Our investigation reveals that OPRO shows limited effectiveness in small-scale LLMs, with limited inference capabilities constraining optimization ability.

Revisiting OPRO: The Limitations of Small-Scale LLMs as Optimizers · Around

Built on

Pytorch: An imperative style, high performance deep learning library
Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, Alban Desmasion, Andreas Kopf, Edward Yang, Zachary DeVito, Martin Raison, Alykhan Tejani, Sasank Chilamkurthy, Benoit Steiner, Lu Fang, Junjie Bai, and Soumith Chintala. 2019 · 2019
Earlier work this paper cites.
Revisiting automated prompting: Are we actually doing better?
Yulin Zhou, Yiren Zhao, Ilia Shumailov, Robert Mullins, and Yarin Gal. 2023 · 2019
Earlier work this paper cites.
Language models are few-shot learners
OpenAI. 2020 · 2020
Earlier work this paper cites.
Gpt understands, too
Original
Xiao Liu, Yanan Zheng, Zhengxiao Du, Ming Ding, Yujie Qian, Zhilin Yang, and Jie Tang. 2021 · 2021
Earlier work this paper cites.
Large language models are zero-shot reasoners
Takeshi Kojima, Shixiang Shane Gu, Machel Reid, Yutaka Matsuo, and Yusuke Iwasawa. 2022 · 2022
Earlier work this paper cites.
Self-consistency improves chain of thought reasoning in language models
Original
Xuezhi Wang, Jason Wei, Dale Schuurmans, Quoc Le, Ed Huai hsin Chi, and Denny Zhou. 2022 · 2022
Earlier work this paper cites.
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
Earlier work this paper cites.

Similar

Large language models are human-level prompt engineers
Original
Yongchao Zhou, Andrei Ioan Muresanu, Ziwen Han, Keiran Paster, Silviu Pitis, Harris Chan, and Jimmy Ba. 2022 · 2022
Cited alongside, same era.
Promptbreeder: Self-referential self-improvement via prompt evolution
Original
Chrisantha Fernando, Dylan S. Banarse, Henryk Michalewski, Simon Osindero, and Tim Rocktäschel. 2023 · 2023
Cited alongside, same era.
Gemini: A family of highly capable multimodal models
Original
Google Gemini Team. 2023 · 2023
Cited alongside, same era.
Connecting large language models with evolutionary algorithms yields powerful prompt optimizers
Original
Qingyan Guo, Rui Wang, Junliang Guo, Bei Li, Kaitao Song, Xu Tan, Guoqing Liu, Jiang Bian, Yujiu Yang, Tsinghua University, and Microsoft Research. 2023 · 2023
Cited alongside, same era.

Then

Automatic prompt optimization with "gradient descent" and beam search
Reid Pryzant, Dan Iter, Jerry Li, Yin Tat Lee, Chenguang Zhu, and Michael Zeng. 2023 · 2023
Later among the works it cites.
Llama 2: Open foundation and fine-tuned chat models
Original
Hugo Touvron, Louis Martin, Kevin R. Stone, Peter Albert, et al. 2023 · 2023
Later among the works it cites.
Efficient large language models: A survey
Original
Zhongwei Wan, Xin Wang, Che Liu, Samiul Alam, Yu Zheng, Jiachen Liu, Zhongnan Qu, Shen Yan, Yi Zhu, Quanlu Zhang, Mosharaf Chowdhury, and Mi Zhang. 2023 · 2023
Later among the works it cites.
Large language models as optimizers
Original
Chengrun Yang, Xuezhi Wang, Yifeng Lu, Hanxiao Liu, Quoc V Le, Denny Zhou, and Xinyun Chen. 2023 · 2023
Later among the works it cites.
Tree of thoughts: Deliberate problem solving with large language models

Beyond the bibliography

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

Open on alphaXiv

alphaXiv is searching for related work…

Distilling step-by-step! outperforming larger language models with less training data and smaller model sizes

Original

Cheng-Yu Hsieh, Chun-Liang Li, Chih-Kuan Yeh, Hootan Nakhost, Yasuhisa Fujii, Alexander J. Ratner, Ranjay Krishna, Chen-Yu Lee, and Tomas Pfister. 2023 · 2023

Cited alongside, same era.

Large language models cannot self-correct reasoning yet

Original

Jie Huang, Xinyun Chen, Swaroop Mishra, Huaixiu Steven Zheng, Adams Wei Yu, Xinying Song, and Denny Zhou. 2023 · 2023

Cited alongside, same era.

Original

Albert Qiaochu Jiang, Alexandre Sablayrolles, Arthur Mensch, Chris Bamford, Devendra Singh Chaplot, Diego de Las Casas, Florian Bressand, Gianna Lengyel, Guillaume Lample, Lucile Saulnier, L’elio Renard Lavaud, Marie-Anne Lachaux, Pierre Stock, Teven Le Scao, Thibaut Lavril, Thomas Wang, Timothée Lacroix, and William El Sayed. 2023 · 2023

Cited alongside, same era.

Shunyu Yao, Dian Yu, Jeffrey Zhao, Izhak Shafran, Thomas L. Griffiths, Yuan Cao, and Karthik Narasimhan. 2023 · 2023

Later among the works it cites.

Are large language models good prompt optimizers?

Ruotian Ma, Xiaolei Wang, Xin Zhou, Jian Li, Nan Du, Tao Gui, Qi Zhang, and Xuanjing Huang. 2024 · 2024

Closest in time.