temporal-graph-gen
self-refine
| temporal-graph-gen | self-refine | |
|---|---|---|
| 3 | 8 | |
| 15 | 495 | |
| - | - | |
| 0.0 | 7.9 | |
| almost 3 years ago | 4 months ago | |
| Python | Python | |
| MIT License | Apache License 2.0 |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
temporal-graph-gen
-
GraphGPT: Extrapolating knowledge graphs from unstructured text
It has been possible to generate impressive graphs from text since GPT-2. Though you need a few tricks to make it work.
Here's an example (my work): https://aclanthology.org/2021.naacl-main.67.pdf
TLDR of the input/output: https://madaan.github.io/res/tldr/graph_gen_tldr.jpg
- [D] Autoregressive model for graph generation?
-
Online Text to Diagram Tools
On a related note, I did some work on generating temporal graphs from text: https://arxiv.org/pdf/2010.10077.pdf
Code/models: https://github.com/madaan/temporal-graph-gen
self-refine
- Self-Refine: Iterative Refinement with Self-Feedback
-
ChemCrow: Augmenting large-language models with chemistry tools
>the systems operation are well understood
That's like saying human behavior is well understood because we know how neurons communicate signals. It's too low level to be useful, hence psychology.
>They don't have the ability to reason or reflect.
Yes they do
https://selfrefine.info/
https://arxiv.org/abs/2303.11366
-
Generative Agents: Interactive Simulacra of Human Behavior
Literally you've been told it doesn't need that much handholding.
https://selfrefine.info/
-
Large Language Models Are Human-Level Prompt Engineers
For those curious about self-refining systems: https://selfrefine.info/ (our recent work).
-
This AI Paper Introduces SELF-REFINE: A Framework For Improving Initial Outputs From LLMs Through Iterative Feedback And Refinement
Project: https://selfrefine.info/
-
Self-Refine: Iterative Refinement with Self-Feedback - a novel approach that allows LLMs to iteratively refine outputs and incorporate feedback along multiple dimensions to improve performance on diverse tasks
Found relevant code at https://github.com/madaan/self-refine + all code implementations here
What are some alternatives?
GraphGPT - Extrapolating knowledge graphs from unstructured text using GPT-3 🕵️♂️
AutoGPTQ - An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.
spark-joy - ✨😂 2000+ ways to add design flair, user delight, and whimsy to your product.
prompt-lib - A set of utilities for running few-shot prompting experiments on large-language models
Graphormer - Graphormer is a general-purpose deep learning backbone for molecular modeling.
pal - PaL: Program-Aided Language Models (ICML 2023)
dagre-svg
KeenWrite - Free, open-source, cross-platform desktop Markdown text editor with live preview, string interpolation, and math.