JayZhang42/SLED
SLED: Self Logits Evolution Decoding for Improving Factuality in Large Language Model https://arxiv.org/pdf/2411.02433
SLED helps AI engineers and researchers improve the factual accuracy of Large Language Models (LLMs). It takes an existing LLM and enhances its ability to generate truthful responses by subtly adjusting its internal decision-making process. The output is a more reliable and factually consistent text generation, without significant extra computational cost.
119 stars. No commits in the last 6 months.
Use this if you need to make your large language models less prone to 'hallucinations' and more factual across various question-answering, reasoning, or content generation tasks.
Not ideal if your primary concern is generating highly creative or diverse text where strict factual accuracy is a secondary concern.
Stars
119
Forks
20
Language
Python
License
—
Category
Last pushed
Dec 05, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/JayZhang42/SLED"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
PaddlePaddle/PaddleNLP
Easy-to-use and powerful LLM and SLM library with awesome model zoo.
meta-llama/llama-cookbook
Welcome to the Llama Cookbook! This is your go to guide for Building with Llama: Getting started...
arcee-ai/mergekit
Tools for merging pretrained large language models.
changyeyu/LLM-RL-Visualized
๐100+ ๅๅ LLM / RL ๅ็ๅพ๐๏ผใๅคงๆจกๅ็ฎๆณใไฝ่ ๅทจ็ฎ๏ผ๐ฅ๏ผ100+ LLM/RL Algorithm Maps ๏ผ
mindspore-lab/step_into_llm
MindSpore online courses: Step into LLM