paper-with-me

Papers

Automatic Prompt Optimization with Prompt Distillation

2025-08-26 · Ernest A. Dyagin, Nikita I. Kulin, Artur R. Khairullin, Viktor N. Zhuravlev, Alena N. Sitkina arxiv

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.

📄 PDF Abstract BibTeX arXiv:2508.18992

Code (0)

등록된 구현이 없습니다.

Tasks

Text ClassificationPrompt Engineering

Similar Papers 제목 키워드 기반

Concept Distillation from Strong to Weak Models via Hypotheses-to-Theories Prompting

2024-08-18 · Emmanuel Aboah Boateng, Cassiano O. Becker, Nabiha Asghar, Kabir Walia 외

Hand-crafting high quality prompts to optimize the performance of language models is a complicated and labor-intensive process. Furthermore, when migrating to newer, smaller, or weaker models (possibly due to latency or …

HumanEvalMathematical Reasoning

Local Prompt Optimization

2025-04-29 · Yash Jain, Vishal Chowdhary

In recent years, the use of prompts to guide the output of Large Language Models have increased dramatically. However, even the best of experts struggle to choose the correct words to stitch up a prompt for the desired t…

GSM8KMathPrompt Engineering

Verbalizing Subliminal Learning Effects Using Text Optimization

2026-09-15 · Nathan Hu, Sanmi Koyejo, Christopher Potts arxiv

Subliminal learning is a phenomenon in which a distillation dataset transmits traits from the teacher model that are not legibly encoded in the dataset itself. This introduces a new challenge for model development and cr…

ModeDreamer: Mode Guiding Score Distillation for Text-to-3D Generation using Reference Image Prompts

2024-11-27 · Uy Dieu Tran, Minh Luu, Phong Ha Nguyen, Khoi Nguyen 외

Existing Score Distillation Sampling (SDS)-based methods have driven significant progress in text-to-3D generation. However, 3D models produced by SDS-based methods tend to exhibit over-smoothing and low-quality outputs.…

3D GenerationText to 3D

Target-Balanced Score Distillation

2025-11-12 · Zhou Xu, Qi Wang, Yuxiao Yang, Luyuan Zhang 외 arxiv

Score Distillation Sampling (SDS) enables 3D asset generation by distilling priors from pretrained 2D text-to-image diffusion models, but vanilla SDS suffers from over-saturation and over-smoothing. To mitigate this issu…