Automatic Prompt Optimization with "Gradient Descent" and Beam Search

• URL: http://arxiv.org/abs/2305.03495v2
• Date: Thu, 19 Oct 2023 04:37:25 GMT
• Title: Automatic Prompt Optimization with "Gradient Descent" and Beam Search
• Authors: Reid Pryzant, Dan Iter, Jerry Li, Yin Tat Lee, Chenguang Zhu, Michael Zeng
• Abstract summary: Large Language Models (LLMs) have shown impressive performance as general purpose agents, but their abilities remain highly dependent on prompts. We propose a simple and nonparametric solution to this problem, Automatic Prompt Optimization (APO) APO uses minibatches of data to form natural language "gradients" that criticize the current prompt. The gradients are then "propagated" into the prompt by editing the prompt in the opposite semantic direction of the gradient.
• Score: 64.08364384823645
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large Language Models (LLMs) have shown impressive performance as general purpose agents, but their abilities remain highly dependent on prompts which are hand written with onerous trial-and-error effort. We propose a simple and nonparametric solution to this problem, Automatic Prompt Optimization (APO), which is inspired by numerical gradient descent to automatically improve prompts, assuming access to training data and an LLM API. The algorithm uses minibatches of data to form natural language "gradients" that criticize the current prompt. The gradients are then "propagated" into the prompt by editing the prompt in the opposite semantic direction of the gradient. These gradient descent steps are guided by a beam search and bandit selection procedure which significantly improves algorithmic efficiency. Preliminary results across three benchmark NLP tasks and the novel problem of LLM jailbreak detection suggest that Automatic Prompt Optimization can outperform prior prompt editing techniques and improve an initial prompt's performance by up to 31%, by using data to rewrite vague task descriptions into more precise annotation instructions.

Related papers

• Gradient-Mask Tuning Elevates the Upper Limits of LLM Performance [51.36243421001282]
  Gradient-Mask Tuning (GMT) is a method that selectively updates parameters during training based on their gradient information. Our empirical results across various tasks demonstrate that GMT not only outperforms traditional fine-tuning methods but also elevates the upper limits of LLM performance.
  arXiv  Detail & Related papers  (2024-06-21T17:42:52Z)
• APEER: Automatic Prompt Engineering Enhances Large Language Model Reranking [39.649879274238856]
  We introduce a novel automatic prompt engineering algorithm named APEER. APEER iteratively generates refined prompts through feedback and preference optimization. Experiments demonstrate the substantial performance improvement of APEER over existing state-of-the-art (SoTA) manual prompts.
  arXiv  Detail & Related papers  (2024-06-20T16:11:45Z)
• Superposition Prompting: Improving and Accelerating Retrieval-Augmented Generation [22.124234811959532]
  Large language models (LLMs) exhibit significant drawbacks when processing long contexts. We propose a novel RAG prompting methodology, which can be directly applied to pre-trained transformer-based LLMs. We demonstrate the capability of our method to simultaneously enhance time efficiency across a variety of question-answering benchmarks.
  arXiv  Detail & Related papers  (2024-04-10T11:03:17Z)
• Efficient Prompting Methods for Large Language Models: A Survey [50.171011917404485]
  Prompting has become a mainstream paradigm for adapting large language models (LLMs) to specific natural language processing tasks. This approach brings the additional computational burden of model inference and human effort to guide and control the behavior of LLMs. We present the basic concepts of prompting, review the advances for efficient prompting, and highlight future research directions.
  arXiv  Detail & Related papers  (2024-04-01T12:19:08Z)
• Intent-based Prompt Calibration: Enhancing prompt optimization with synthetic boundary cases [2.6159111710501506]
  We introduce a new method for automatic prompt engineering, using a calibration process that iteratively refines the prompt to the user intent. We demonstrate the effectiveness of our method with respect to strong proprietary models on real-world tasks such as moderation and generation.
  arXiv  Detail & Related papers  (2024-02-05T15:28:43Z)
• AutoHint: Automatic Prompt Optimization with Hint Generation [11.737818328656735]
  This paper presents AutoHint, a novel framework for automatic prompt engineering and optimization for Large Language Models (LLM) We propose a framework to inherit the merits of both in-context learning and zero-shot learning by incorporating enriched instructions derived from input-output demonstrations to optimize original prompt. We refer to the enrichment as the hint and propose a framework to automatically generate the hint from labeled data.
  arXiv  Detail & Related papers  (2023-07-13T00:49:27Z)
• 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)
• RLPrompt: Optimizing Discrete Text Prompts With Reinforcement Learning [84.75064077323098]
  This paper proposes RLPrompt, an efficient discrete prompt optimization approach with reinforcement learning (RL) RLPrompt is flexibly applicable to different types of LMs, such as masked gibberish (e.g., grammaBERT) and left-to-right models (e.g., GPTs) Experiments on few-shot classification and unsupervised text style transfer show superior performance over a wide range of existing finetuning or prompting methods.
  arXiv  Detail & Related papers  (2022-05-25T07:50:31Z)
• GrIPS: Gradient-free, Edit-based Instruction Search for Prompting Large Language Models [80.03815493269522]
  GrIPS is a gradient-free, edit-based search approach for improving task instructions for large language models. With InstructGPT models, GrIPS improves the average task performance by up to 4.30 percentage points on eight classification tasks. We show our edits can simplify instructions and at times make them incoherent but nonetheless improve accuracy.
  arXiv  Detail & Related papers  (2022-03-14T16:54:46Z)

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.