paper-with-me

홈 › Papers

Bandit-Based Prompt Design Strategy Selection Improves Prompt Optimizers

2025-03-03 · Rin Ashizawa, Yoichi Hirose, Nozomu Yoshinari, Kento Uchida, Shinichi Shirakawa

Prompt optimization aims to search for effective prompts that enhance the performance of large language models (LLMs). Although existing prompt optimization methods have discovered effective prompts, they often differ from sophisticated prompts carefully designed by human experts. Prompt design strategies, representing best practices for improving prompt performance, can be key to improving prompt optimization. Recently, a method termed the Autonomous Prompt Engineering Toolbox (APET) has incorporated various prompt design strategies into the prompt optimization process. In APET, the LLM is needed to implicitly select and apply the appropriate strategies because prompt design strategies can have negative effects. This implicit selection may be suboptimal due to the limited optimization capabilities of LLMs. This paper introduces Optimizing Prompts with sTrategy Selection (OPTS), which implements explicit selection mechanisms for prompt design. We propose three mechanisms, including a Thompson sampling-based approach, and integrate them into EvoPrompt, a well-known prompt optimizer. Experiments optimizing prompts for two LLMs, Llama-3-8B-Instruct and GPT-4o mini, were conducted using BIG-Bench Hard. Our results show that the selection of prompt design strategies improves the performance of EvoPrompt, and the Thompson sampling-based mechanism achieves the best overall results. Our experimental code is provided at https://github.com/shiralab/OPTS .

📄 PDF Abstract BibTeX arXiv:2503.01163

Code (1)

shiralab/opts 공식 구현

Tasks

Prompt EngineeringThompson Sampling

Similar Papers 제목 키워드 기반

Object Search in Partially-Known Environments via LLM-informed Model-based Planning and Prompt Selection

2026-03-25 · Abhishek Paudel, Abhish Khanal, Raihan I. Arnob, Shahriar Hossain 외 arxiv

We present a novel LLM-informed model-based planning framework, and a novel prompt selection method, for object search in partially-known environments. Our approach uses an LLM to estimate statistics about the likelihood…

Efficient Multi-objective Prompt Optimization via Pure-exploration Bandits

2026-05-14 · Donghao Li, Chengshuai Shi, Weijuan Ou, Cong Shen 외 arxiv

Prompt engineering has become central to eliciting the capabilities of large language models (LLMs). At its core lies prompt selection -- efficiently identifying the most effective prompts. However, most prior investigat…

Prompt Engineering

Task Selection for Bandit-Based Task Assignment in Heterogeneous Crowdsourcing

2015-07-26 · Hao Zhang, Masashi Sugiyama

Task selection (picking an appropriate labeling task) and worker selection (assigning the labeling task to a suitable worker) are two major challenges in task assignment for crowdsourcing. Recently, worker selection has …

Active Learning

Efficient Prompt Optimization Through the Lens of Best Arm Identification

2024-02-15 · Chengshuai Shi, Kun Yang, Zihan Chen, Jundong Li 외

The remarkable instruction-following capability of large language models (LLMs) has sparked a growing interest in automatically finding good prompts, i.e., prompt optimization. Most existing works follow the scheme of se…

Instruction FollowingMulti-Armed Bandits

Max-Utility Based Arm Selection Strategy For Sequential Query Recommendations

2021-08-31 · Shameem A. Puthiya Parambath, Christos Anagnostopoulos, Roderick Murray-Smith, Sean MacAvaney 외

We consider the query recommendation problem in closed loop interactive learning settings like online information gathering and exploratory analytics. The problem can be naturally modelled using the Multi-Armed Bandits (…

Multi-Armed Bandits