Addendum 8
Instruction tuning: https://en.wikipedia.org/wiki/Large_language_model#Instruction_tuning
* self-instruct approaches
* enable LLM to bootstrap correct responses
Instruction Tuning for Large Language Models: Survey
https://arxiv.org/abs/2308.10792
*instruction tuning (IT): further supervised training of LLMs on dataset of (instruction, output) pairs
* enhances capabilities, control of LLM
* bridges gap betw. next-word prediction obj. of LLM & users' obj. of LLM adhering to human instructions
GNU social JP is a social network, courtesy of GNU social JP管理人. It runs on GNU social, version 2.0.2-dev, available under the GNU Affero General Public License.
All GNU social JP content and data are available under the Creative Commons Attribution 3.0 license.