CONNECTING LARGE LANGUAGE MODELS WITH EVOLUTIONARY ALGORITHMS YIELDS POWERFUL PROMPT OPTIMIZERS
Organization
Scaling and Intelligence Lab (SaIL)
Abstract
Large Language Models (LLMs) excel in various tasks, but they rely on carefully
crafted prompts that often demand substantial human effort. To automate this process, in this paper, we propose a novel framework for discrete prompt optimization,
called EVOPROMPT, which borrows the idea of evolutionary algorithms (EAs) as
they exhibit good performance and fast convergence. To enable EAs to work on
discrete prompts, which are natural language expressions that need to be coherent
and human-readable, we connect LLMs with EAs. This approach allows us to
simultaneously leverage the powerful language processing capabilities of LLMs
and the efficient optimization performance of EAs. Specifically, abstaining from
any gradients or parameters, EVOPROMPT starts from a population of prompts
and iteratively generates new prompts with LLMs based on the evolutionary operators, improving the population based on the development set. We optimize
prompts for both closed- and open-source LLMs including GPT-3.5 and Alpaca,
on 9 datasets spanning language understanding and generation tasks. EVOPROMPT
significantly outperforms human-engineered prompts and existing methods for
automatic prompt generation by up to 25% and 14% respectively. Furthermore,
EVOPROMPT demonstrates that connecting LLMs with EAs creates synergies,
which could inspire further research on the combination of LLMs and conventional
algorithms.
crafted prompts that often demand substantial human effort. To automate this process, in this paper, we propose a novel framework for discrete prompt optimization,
called EVOPROMPT, which borrows the idea of evolutionary algorithms (EAs) as
they exhibit good performance and fast convergence. To enable EAs to work on
discrete prompts, which are natural language expressions that need to be coherent
and human-readable, we connect LLMs with EAs. This approach allows us to
simultaneously leverage the powerful language processing capabilities of LLMs
and the efficient optimization performance of EAs. Specifically, abstaining from
any gradients or parameters, EVOPROMPT starts from a population of prompts
and iteratively generates new prompts with LLMs based on the evolutionary operators, improving the population based on the development set. We optimize
prompts for both closed- and open-source LLMs including GPT-3.5 and Alpaca,
on 9 datasets spanning language understanding and generation tasks. EVOPROMPT
significantly outperforms human-engineered prompts and existing methods for
automatic prompt generation by up to 25% and 14% respectively. Furthermore,
EVOPROMPT demonstrates that connecting LLMs with EAs creates synergies,
which could inspire further research on the combination of LLMs and conventional
algorithms.
Graduation Theses defence year
2023-2024
Supervisor
Kallol Roy
Spoken language (s)
English
Requirements for candidates
Level
Bachelor, Masters
Application of contact
Name
Kallol Roy
Phone
+37256051480
E-mail
See more