PhaseEvo: Towards Unified In-Context Prompt Optimization for Large
Language Models
- URL: http://arxiv.org/abs/2402.11347v1
- Date: Sat, 17 Feb 2024 17:47:10 GMT
- Title: PhaseEvo: Towards Unified In-Context Prompt Optimization for Large
Language Models
- Authors: Wendi Cui, Jiaxin Zhang, Zhuohang Li, Hao Sun, Damien Lopez, Kamalika
Das, Bradley Malin, Sricharan Kumar
- Abstract summary: We present PhaseEvo, an efficient automatic prompt optimization framework that combines the generative capability of LLMs with the global search proficiency of evolution algorithms.
PhaseEvo significantly outperforms the state-of-the-art baseline methods by a large margin whilst maintaining good efficiency.
- Score: 9.362082187605356
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Crafting an ideal prompt for Large Language Models (LLMs) is a challenging
task that demands significant resources and expert human input. Existing work
treats the optimization of prompt instruction and in-context learning examples
as distinct problems, leading to sub-optimal prompt performance. This research
addresses this limitation by establishing a unified in-context prompt
optimization framework, which aims to achieve joint optimization of the prompt
instruction and examples. However, formulating such optimization in the
discrete and high-dimensional natural language space introduces challenges in
terms of convergence and computational efficiency. To overcome these issues, we
present PhaseEvo, an efficient automatic prompt optimization framework that
combines the generative capability of LLMs with the global search proficiency
of evolution algorithms. Our framework features a multi-phase design
incorporating innovative LLM-based mutation operators to enhance search
efficiency and accelerate convergence. We conduct an extensive evaluation of
our approach across 35 benchmark tasks. The results demonstrate that PhaseEvo
significantly outperforms the state-of-the-art baseline methods by a large
margin whilst maintaining good efficiency.
Related papers
- MAPO: Boosting Large Language Model Performance with Model-Adaptive Prompt Optimization [73.7779735046424]
We show that different prompts should be adapted to different Large Language Models (LLM) to enhance their capabilities across various downstream tasks in NLP.
We then propose a model-adaptive prompt (MAPO) method that optimize the original prompts for each specific LLM in downstream tasks.
arXiv Detail & Related papers (2024-07-04T18:39:59Z) - Large Language Model-Aided Evolutionary Search for Constrained Multiobjective Optimization [15.476478159958416]
We employ a large language model (LLM) to enhance evolutionary search for solving constrained multi-objective optimization problems.
Our aim is to speed up the convergence of the evolutionary population.
arXiv Detail & Related papers (2024-05-09T13:44:04Z) - Localized Zeroth-Order Prompt Optimization [54.964765668688806]
We propose a novel algorithm, namely localized zeroth-order prompt optimization (ZOPO)
ZOPO incorporates a Neural Tangent Kernel-based derived Gaussian process into standard zeroth-order optimization for an efficient search of well-performing local optima in prompt optimization.
Remarkably, ZOPO outperforms existing baselines in terms of both the optimization performance and the query efficiency.
arXiv Detail & Related papers (2024-03-05T14:18:15Z) - How Multimodal Integration Boost the Performance of LLM for
Optimization: Case Study on Capacitated Vehicle Routing Problems [33.33996058215666]
Large language models (LLMs) have positioned themselves as capable tools for addressing complex optimization challenges.
We propose to enhance the optimization performance using multimodal LLM capable of processing both textual and visual prompts.
arXiv Detail & Related papers (2024-03-04T06:24:21Z) - Large Language Models to Enhance Bayesian Optimization [57.474613739645605]
We present LLAMBO, a novel approach that integrates the capabilities of Large Language Models (LLM) within Bayesian optimization.
At a high level, we frame the BO problem in natural language, enabling LLMs to iteratively propose and evaluate promising solutions conditioned on historical evaluations.
Our findings illustrate that LLAMBO is effective at zero-shot warmstarting, and enhances surrogate modeling and candidate sampling, especially in the early stages of search when observations are sparse.
arXiv Detail & Related papers (2024-02-06T11:44:06Z) - Connecting Large Language Models with Evolutionary Algorithms Yields
Powerful Prompt Optimizers [70.18534453485849]
EvoPrompt is a framework for discrete prompt optimization.
It borrows the idea of evolutionary algorithms (EAs) as they exhibit good performance and fast convergence.
It significantly outperforms human-engineered prompts and existing methods for automatic prompt generation.
arXiv Detail & Related papers (2023-09-15T16:50:09Z) - Query-Dependent Prompt Evaluation and Optimization with Offline Inverse
RL [62.824464372594576]
We aim to enhance arithmetic reasoning ability of Large Language Models (LLMs) through zero-shot prompt optimization.
We identify a previously overlooked objective of query dependency in such optimization.
We introduce Prompt-OIRL, which harnesses offline inverse reinforcement learning to draw insights from offline prompting demonstration data.
arXiv Detail & Related papers (2023-09-13T01:12:52Z) - Robust Prompt Optimization for Large Language Models Against
Distribution Shifts [80.6757997074956]
Large Language Model (LLM) has demonstrated significant ability in various Natural Language Processing tasks.
We propose a new problem of robust prompt optimization for LLMs against distribution shifts.
This problem requires the prompt optimized over the labeled source group can simultaneously generalize to an unlabeled target group.
arXiv Detail & Related papers (2023-05-23T11:30:43Z)
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.