question_generation VS FLAML

I have seen models which do something similar but the questions they ask are not in a Yes/No style such as this T5 - based Question Generator. Essentially, I was wondering how I would go about developing such a model.

I've been able to get good domain-specific performance out of RoBERTa by training it on SQuAD (general QA) and synthetic domain-specific data created via https://github.com/patil-suraj/question_generation, took about 1000 domain-specific QA pairs.

Not sure if it's SOTA but this project and paper is really interesting and quite easy to use : https://github.com/patil-suraj/question_generation

Take a look at https://github.com/patil-suraj/question_generation . It's a T5 model that tuned for generating questions for multiple formats (reading comprehension, multiple choice, cloze, etc) given an input text.

I really like the simplicity of this framework, and they hit on a lot of common problems found in other agent-based frameworks. Most intrigued by the RAG improvements.

Seems like Microsoft was frustrated with the pace of movement in this space and the shitty results of agents (which admittedly kept my interest turned away from agents for the last few months). I'm interested again because it makes practical sense, and from looking at the example notebooks, seems fairly easy to integrate into existing applications.

Maybe this is the 'low code' approach that might actually work, and bridge together engineering and non-engineering resources.

This example was what caught my eye: https://github.com/microsoft/FLAML/blob/main/notebook/autoge...

4. FLAML

Improved AutoML - Again, with collaboration from Microsoft Research, we used FLAML to update our existing AutoML solutions. What does this mean for you? You're using the latest techniques but all you need is a problem to solve and some data to get started.

For a complete tutorial, navigate to this Jupyter Notebook: https://github.com/microsoft/FLAML/blob/main/notebook/flaml_automl.ipynb

Microsoft Researchers have developed FLAML (Fast Lightweight AutoML) which can now utilize Ray Tune for distributed hyperparameter tuning to scale up FLAML’s resource-efficient & seamlessly parallelizable algorithms across a cluster.

Looks nice but I wonder if this is practical for non-tiny problems. The papers are a bit hard to follow but it looks like training is restarted with every new architecture choice. As for the library itself, the only large neural net example is a finetune of an NLP model that only searches over ADAM's optimizer params - which could be useful but it's a stretch to call that AutoML.