Meta Prompting for AI Systems
- URL: http://arxiv.org/abs/2311.11482v7
- Date: Wed, 26 Feb 2025 05:39:39 GMT
- Title: Meta Prompting for AI Systems
- Authors: Yifan Zhang, Yang Yuan, Andrew Chi-Chih Yao,
- Abstract summary: We introduce Meta Prompting (MP), a prompting paradigm designed to enhance the utilization of large language models and AI systems.<n>MP prioritizes structural and syntactical considerations over traditional content-centric methods.<n> Empirical evaluations reveal that a Qwen-72B base language model equipped with Meta Prompting-without additional instruction tuning-achieves a PASS@1 accuracy of 46.3%.
- Score: 12.304069891580658
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: We introduce Meta Prompting (MP), a prompting paradigm designed to enhance the utilization of large language models (LLMs) and AI systems in complex problem-solving and data interaction. Grounded in type theory and category theory, Meta Prompting prioritizes structural and syntactical considerations over traditional content-centric methods. In this work, we formally define Meta Prompting, delineate its distinctions from few-shot prompting, and demonstrate its effectiveness across various AI applications. In particular, we show that Meta Prompting can decompose intricate reasoning tasks into simpler sub-problems, thereby improving token efficiency and enabling fairer comparisons with conventional few-shot techniques. Furthermore, we extend this framework to prompting tasks, allowing LLMs to recursively self-generate refined prompts in a metaprogramming-like manner. Empirical evaluations reveal that a Qwen-72B base language model equipped with Meta Prompting-without additional instruction tuning-achieves a PASS@1 accuracy of 46.3% on MATH problems, surpassing a supervised fine-tuned counterpart, 83.5% accuracy on GSM8K, and a 100% success rate on Game of 24 tasks using GPT-4. The code is available at https://github.com/meta-prompting/meta-prompting.
Related papers
- MetaKP: On-Demand Keyphrase Generation [52.48698290354449]
We introduce on-demand keyphrase generation, a novel paradigm that requires keyphrases that conform to specific high-level goals or intents.
We present MetaKP, a large-scale benchmark comprising four datasets, 7500 documents, and 3760 goals across news and biomedical domains with human-annotated keyphrases.
We demonstrate the potential of our method to serve as a general NLP infrastructure, exemplified by its application in epidemic event detection from social media.
arXiv Detail & Related papers (2024-06-28T19:02:59Z) - Prompt Learning via Meta-Regularization [18.518214936430816]
We propose a Prompt Meta-Regularization (ProMetaR) to improve the generalizability of prompt learning for vision-language models.
ProMetaR meta-learns both the regularizer and the soft prompts to harness the task-specific knowledge from the downstream tasks and task-agnostic general knowledge from the vision-language models.
arXiv Detail & Related papers (2024-04-01T01:42:23Z) - Meta-Prompting: Enhancing Language Models with Task-Agnostic Scaffolding [15.04954445749935]
We introduce meta-prompting, an effective scaffolding technique designed to enhance the functionality of language models (LMs)
By employing high-level instructions, meta-prompting guides the LM to break down complex tasks into smaller, more manageable subtasks.
Central to this process is the LM itself, in its role as the conductor, which ensures seamless communication and effective integration of the outputs.
arXiv Detail & Related papers (2024-01-23T18:22:19Z) - On Meta-Prompting [18.949285430843695]
We call these approaches meta-prompting, or prompting to obtain prompts.
We propose a theoretical framework based on category theory to generalize and describe them.
arXiv Detail & Related papers (2023-12-11T17:46:44Z) - MetricPrompt: Prompting Model as a Relevance Metric for Few-shot Text
Classification [65.51149771074944]
MetricPrompt eases verbalizer design difficulty by reformulating few-shot text classification task into text pair relevance estimation task.
We conduct experiments on three widely used text classification datasets across four few-shot settings.
Results show that MetricPrompt outperforms manual verbalizer and other automatic verbalizer design methods across all few-shot settings.
arXiv Detail & Related papers (2023-06-15T06:51:35Z) - Effective Structured Prompting by Meta-Learning and Representative Verbalizer [27.64413828719264]
We propose MetaPrompter for effective structured prompting.
We propose a novel soft verbalizer (RepVerb) which constructs label embedding from feature embeddings directly.
Experimental results demonstrate that MetaPrompter performs better than the recent state-of-the-arts.
arXiv Detail & Related papers (2023-06-01T12:44:33Z) - Error Analysis Prompting Enables Human-Like Translation Evaluation in Large Language Models [57.80514758695275]
Using large language models (LLMs) for assessing the quality of machine translation (MT) achieves state-of-the-art performance at the system level.
We propose a new prompting method called textbftextttError Analysis Prompting (EAPrompt)
This technique emulates the commonly accepted human evaluation framework - Multidimensional Quality Metrics (MQM) and textitproduces explainable and reliable MT evaluations at both the system and segment level.
arXiv Detail & Related papers (2023-03-24T05:05:03Z) - Self-supervised Meta-Prompt Learning with Meta-Gradient Regularization
for Few-shot Generalization [40.45470744120691]
Self-sUpervised meta-Prompt learning framework with MEta-gradient Regularization for few-shot generalization (SUPMER)
This paper proposes a novel Self-sUpervised meta-Prompt learning framework with MEta-gradient Regularization for few-shot generalization (SUPMER)
arXiv Detail & Related papers (2023-03-22T05:04:21Z) - TEMPERA: Test-Time Prompting via Reinforcement Learning [57.48657629588436]
We propose Test-time Prompt Editing using Reinforcement learning (TEMPERA)
In contrast to prior prompt generation methods, TEMPERA can efficiently leverage prior knowledge.
Our method achieves 5.33x on average improvement in sample efficiency when compared to the traditional fine-tuning methods.
arXiv Detail & Related papers (2022-11-21T22:38:20Z) - MetaPrompting: Learning to Learn Better Prompts [52.914694884515534]
We propose a new soft prompting method called MetaPrompting, which adopts the well-recognized model-agnostic meta-learning algorithm.
Extensive experiments show MetaPrompting brings significant improvement on four different datasets.
arXiv Detail & Related papers (2022-09-23T09:01:05Z) - Instance-wise Prompt Tuning for Pretrained Language Models [72.74916121511662]
Instance-wise Prompt Tuning (IPT) is the first prompt learning paradigm that injects knowledge from the input data instances to the prompts.
IPT significantly outperforms task-based prompt learning methods, and achieves comparable performance to conventional finetuning with only 0.5% - 1.5% of tuned parameters.
arXiv Detail & Related papers (2022-06-04T10:08:50Z) - Set-based Meta-Interpolation for Few-Task Meta-Learning [79.4236527774689]
We propose a novel domain-agnostic task augmentation method, Meta-Interpolation, to densify the meta-training task distribution.
We empirically validate the efficacy of Meta-Interpolation on eight datasets spanning across various domains.
arXiv Detail & Related papers (2022-05-20T06:53:03Z) - CINS: Comprehensive Instruction for Few-shot Learning in Task-oriented
Dialog Systems [56.302581679816775]
This paper proposes Comprehensive Instruction (CINS) that exploits PLMs with task-specific instructions.
We design a schema (definition, constraint, prompt) of instructions and their customized realizations for three important downstream tasks in ToD.
Experiments are conducted on these ToD tasks in realistic few-shot learning scenarios with small validation data.
arXiv Detail & Related papers (2021-09-10T03:23:06Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.