Refining the Responses of LLMs by Themselves

Tianqiang Yan, Tiansheng Xu
5/6/2023
cs.CLcs.AI

No official code found. Best implementation: henryyantq/OptimaLLM (4 stars, MIT, last commit 2024-08-03).

Abstract

In this paper, we propose a simple yet efficient approach based on prompt engineering that leverages the large language model itself to optimize its answers without relying on auxiliary models. We introduce an iterative self-evaluating optimization mechanism, with the potential for improved output quality as iterations progress, removing the need for manual intervention. The experiment's findings indicate that utilizing our response refinement framework on the GPT-3.5 model yields results that are on par with, or even surpass, those generated by the cutting-edge GPT-4 model. Detailed implementation strategies and illustrative examples are provided to demonstrate the superiority of our proposed solution.

View on arXivView PDF

Code Implementations(1)

henryyantq/OptimaLLMCommunity100%
MIT

The official implementation of the paper Refining the Responses of LLMs by Themselves

40PythonMay 6, 20232 years agoMIT

Similar Papers

SEE: Strategic Exploration and Exploitation for Cohesive In-Context Prompt Optimization

88% match2024

Are Large Language Models Good Prompt Optimizers?

88% match1 repo12024

Solving General Natural-Language-Description Optimization Problems with Large Language Models

88% match2024

Local Prompt Optimization

88% match2025

MODP: Multi Objective Directional Prompting

88% match2025

Unleashing the Potential of Large Language Models as Prompt Optimizers: Analogical Analysis with Gradient-based Model Optimizers

88% match1 repo302024

Cite this paper

@article{yan2023refining,
  title  = {Refining the Responses of LLMs by Themselves},
  author = {Tianqiang Yan and Tiansheng Xu},
  year   = {2023},
  eprint = {2305.04039},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2305.04039v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2305.04039.svg)](https://codeofpaper.com/paper/2305.04039)

Discussion