https://github.com/dimits-ts/llms_prompting_annotation

Practical Data Science assignments relating to LLMs, prompting and annotation tasks.
https://github.com/dimits-ts/llms_prompting_annotation

annotation chatgpt clustering embeddings llms prompt-engineering webscraping word2vec

Last synced: 6 days ago
JSON representation

Practical Data Science assignments relating to LLMs, prompting and annotation tasks.

• Host: GitHub
• URL: https://github.com/dimits-ts/llms_prompting_annotation
• Owner: dimits-ts
• Created: 2023-10-28T08:14:23.000Z (about 1 year ago)
• Default Branch: master
• Last Pushed: 2024-01-04T10:33:51.000Z (12 months ago)
• Last Synced: 2024-11-14T08:49:57.561Z (about 2 months ago)
• Topics: annotation, chatgpt, clustering, embeddings, llms, prompt-engineering, webscraping, word2vec
• Language: Jupyter Notebook
• Homepage:
• Size: 10.2 MB
• Stars: 1
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# LLMs, Prompting, NLP and Annotation

This repository houses several Practical Data Science assignements relating to LLM Prompting (use cases, modern prompting techniques, fail conditions).

The repository is organized as follows:

1. [ChatGPT prompting fail cases](chatgpt/chatgpt-python-prompt.ipynb) where we explore two cases of ChatGPT code generation failing.

2. [LLM prompting for annotation](annotation/annotation.ipynb) where we leverage LLMs to help us in a difficult annotation task, which we then handle by using pandas.

3. [Annotation analysis](ann_stats/ann_stats.ipynb) where we analyze the clustering between different annotators.

4. [Secure-GPT](secure-gpt/SecureGPT_HW4.pptx) a group presentation for a new LLM use-case to make the internet safer - includes fake data generation for demonstration purposes.

5. [Webscraping](webscraping/scraping.ipynb) where we create a webscraper for a Greek gaming forum.

6. [Greek Embedding Plot](embedding-plot/plot.ipynb), in which we create an interquartile range for all the posts in a Greeklish2Greek dataset.

7. [Greek Embedding Creation](greek_embedding/greek_embeddings.ipynb) in which we create and test our own Greek Embeddings.