You cannot select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
16 lines
748 B
Plaintext
16 lines
748 B
Plaintext
2 years ago
|
# Directional Stimulus Prompting
|
||
|
|
||
|
import { Callout, FileTree } from 'nextra-theme-docs'
|
||
|
import {Screenshot} from 'components/screenshot'
|
||
|
import DSP from '../../img/dsp.jpeg'
|
||
|
|
||
|
[Li et al., (2023)](https://arxiv.org/abs/2302.11520) proposes a new prompting technique to better guide the LLM in generating the desired summary.
|
||
|
|
||
|
A tuneable policy LM is trained to generate the stimulus/hint. Seeing more use of RL to optimize LLMs.
|
||
|
|
||
|
The figure below shows how Directional Stimulus Prompting compares with standard prompting. The policy LM can be small and optimized to generate the hints that guide a black-box frozen LLM.
|
||
|
|
||
|
<Screenshot src={DSP} alt="DSP" />
|
||
2 years ago
|
Image Source: [Li et al., (2023)](https://arxiv.org/abs/2302.11520)
|
||
2 years ago
|
|
||
|
Full example coming soon!
|