Submit Your Research Project

Submission information

Submission Number: 14

Submission ID: 10192

Submission UUID: 07f427ba-caac-4570-b8a8-933fe7a8887c

Submission URI: /es/form/submit-your-research-project?check_logged_in=1

Submission View: /es/webform/submit_your_research_project/submissions/10192?token=1yMsfbaiu4-9Tm02C8r_eKZvzMDSyu4Xu6qaQjyV_eY

Submission Update: /es/form/submit-your-research-project?check_logged_in=1&token=1yMsfbaiu4-9Tm02C8r_eKZvzMDSyu4Xu6qaQjyV_eY

Created: Mon, 01/06/2025 - 10:56

Completed: Mon, 01/06/2025 - 10:56

Changed: Mon, 01/06/2025 - 13:02

Remote IP address: 10.64.6.7

Submitted by: mdear2

Language: English

Is draft: No

Webform: Submit Your Research Project

Research Title

Projected Timeline

Start Date

End Date

Research Abstract

This research project investigates the development of an autonomous, iterative pipeline designed to enhance the capabilities of small- to mid-sized large language models (LLMs) by enabling them to refine both system and user prompts for a given task. We explore strategies for self-prompting frameworks in which the LLM iteratively analyzes a user prompt, generates optimized system-level instructions, and refines the prompt to improve task-specific performance in terms of quality and relevance of the generated response.The largest state-of-the-art LLMs often demonstrate superior capabilities. However, smaller models are more accessible for resource-constrained environments, such as edge and personal devices. Enhancing the utility of these lightweight LLMs without fine-tuning or expanding their parameter counts could significantly broaden their practical applications.To assess the effectiveness of this self-prompting framework, the project will establish both qualitative and quantitative benchmarks, including NLP-based similarity scoring and task-specific performance metrics. The interdisciplinary scope will be supported through collaboration with subject matter experts across multiple academic fields to design diverse input prompts and evaluate the quality of the generated outputs.While this project aims to expand the capabilities of resource-efficient LLMs, we also seek to identify reusable, LLM-specific strategies for improving prompt effectiveness across domains. The findings may later be integrated into existing self-correcting LLM pipelines for tasks involving scientific code generation, contributing to the further advancement of autonomous LLM techniques in scientific contexts.

杨贵妃传媒 text formats

Project Type

Faculty

Student

Staff

Lead Researcher(s)

Re-order	Name	Email	Phone	Link	Weight	Operations
	Name	Email	Phone	Link	Item weight
	Name	Email	Phone	Link	Item weight

more items

Assistant Researcher(s)

Re-order	Name	Email	Weight	Operations
	Name	Email	Item weight

more items

Department(s)

Keywords

Associated File(s)

Unlimited number of files can be uploaded to this field.
50 MB limit.
Allowed types: txt, rtf, pdf, doc, docx, odt, ppt, pptx, odp, xls, xlsx, ods.

Has this research project received IRB approval?

Yes

Pending

Not required

Links

Links
	Links Link Title Link URL	Item weight

more items

Comments

Publish

杨贵妃传媒

Request Info

Enlaces del Campus

Enlaces del Sitio