Prompt Learning

Creator

Creator

Created

Created

2023 Sep 5 14:52

Editor

Editor

Edited

Edited

2025 Jul 2 17:17

Refs

Refs

thunlp • Updated 2023 Sep 5 8:32

LM Context Optimization

Language Model Context

Contextual Compression

Prompt Optimization, Prompt Tuning

Prompt changes can significantly impact side effects, so prompt modifications should only be made when they result in Pareto improvements

A process of finding optimized prompts for models with fixed parameters

Fewer tokens

Same meaning

Better results

Prompt Optimization Notion

Prompt Embedding

Prompt Optimization Usages

LARGE LANGUAGE MODELS AS OPTIMIZERS

https://arxiv.org/pdf/2309.03409.pdf

RLPROMPT: Optimizing Discrete Text Prompts with Reinforcement Learning

RLPROMPT: Optimizing Discrete Text Prompts with Reinforcement Learning, EMNLP 2022

https://velog.io/@mmodestaa/RLPROMPT-Optimizing-Discrete-Text-Promptswith-Reinforcement-Learning

RLPROMPT: Optimizing Discrete Text Prompts with Reinforcement Learning

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

Prompting

https://huggingface.co/docs/peft/conceptual_guides/prompting

Prompting

Backlinks

System Prompt Vision Transformer Language Model Context Language Model Context

Recommendations

/////////