Automatic Prompt Optimization with Prompt Distillation

• URL: http://arxiv.org/abs/2508.18992v2
• Date: Mon, 08 Sep 2025 15:50:16 GMT
• Title: Automatic Prompt Optimization with Prompt Distillation
• Authors: Ernest A. Dyagin, Nikita I. Kulin, Artur R. Khairullin, Viktor N. Zhuravlev, Alena N. Sitkina,
• Abstract summary: DistillPrompt is a novel autoprompting method based on large language models.<n>It employs a multi-stage integration of task-specific information into prompts using training data.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Autoprompting is the process of automatically selecting optimized prompts for language models, which is gaining popularity due to the rapid development of prompt engineering driven by extensive research in the field of large language models (LLMs). This paper presents DistillPrompt -- a novel autoprompting method based on large language models that employs a multi-stage integration of task-specific information into prompts using training data. DistillPrompt utilizes distillation, compression, and aggregation operations to explore the prompt space more thoroughly. The method was tested on different datasets for text classification and generation tasks using the t-lite-instruct-0.1 language model. The results demonstrate a significant average improvement (e.g., 20.12% across the entire dataset compared to Grips) in key metrics over existing methods in the field, establishing DistillPrompt as one of the most effective non-gradient approaches in autoprompting.

Related papers

• ReflectivePrompt: Reflective evolution in autoprompting algorithms [0.0]
  ReflectivePrompt is a novel autoprompting method based on evolutionary algorithms.<n>It employs a reflective evolution approach for more precise and comprehensive search of optimal prompts.<n>It was tested on 33 datasets for classification and text generation tasks.
  arXiv  Detail & Related papers  (2025-08-26T09:46:20Z)
• APEER: Automatic Prompt Engineering Enhances Large Language Model Reranking [39.649879274238856]
  We introduce a novel automatic prompt engineering algorithm named APEER.<n>APEER iteratively generates refined prompts through feedback and preference optimization.<n>We find that the prompts generated by APEER exhibit better transferability across diverse tasks and LLMs.
  arXiv  Detail & Related papers  (2024-06-20T16:11:45Z)
• Efficient Prompting Methods for Large Language Models: A Survey [50.82812214830023]
  Efficient Prompting Methods have attracted a wide range of attention.<n>We discuss Automatic Prompt Engineering for different prompt components and Prompt Compression in continuous and discrete spaces.
  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)
• MPrompt: Exploring Multi-level Prompt Tuning for Machine Reading Comprehension [19.12663587559988]
  We propose a multi-level prompt tuning (MPrompt) method for machine reading comprehension. It utilizes prompts at task-specific, domain-specific, and context-specific levels to enhance the comprehension of input semantics. We conducted extensive experiments on 12 benchmarks of various QA formats and achieved an average improvement of 1.94% over the state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-10-27T14:24:06Z)
• 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)
• Automated Few-shot Classification with Instruction-Finetuned Language Models [76.69064714392165]
  We show that AuT-Few outperforms state-of-the-art few-shot learning methods. We also show that AuT-Few is the best ranking method across datasets on the RAFT few-shot benchmark.
  arXiv  Detail & Related papers  (2023-05-21T21:50:27Z)
• 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)
• Interactive and Visual Prompt Engineering for Ad-hoc Task Adaptation with Large Language Models [116.25562358482962]
  State-of-the-art neural language models can be used to solve ad-hoc language tasks without the need for supervised training. PromptIDE allows users to experiment with prompt variations, visualize prompt performance, and iteratively optimize prompts.
  arXiv  Detail & Related papers  (2022-08-16T17:17:53Z)
• Zero-shot Cross-lingual Transfer of Prompt-based Tuning with a Unified Multilingual Prompt [98.26682501616024]
  We propose a novel model that uses a unified prompt for all languages, called UniPrompt. The unified prompt is computation by a multilingual PLM to produce language-independent representation. Our proposed methods can significantly outperform the strong baselines across different languages.
  arXiv  Detail & Related papers  (2022-02-23T11:57:52Z)

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.