cx0/llm-typos

Impact of typos and common misspellings on LLM task performance.

19
/ 100
Experimental

This project helps evaluate how well Large Language Models (LLMs) can handle text containing typos and common misspellings. It takes a piece of text and a target word (which may or may not be misspelled) and measures the LLM's accuracy in finding the words immediately before and after it. This is useful for anyone working with LLMs who needs to understand their robustness when processing imperfect real-world text inputs, such as content from speech-to-text, user-generated content, or unproofread documents.

No commits in the last 6 months.

Use this if you are a researcher or practitioner working with LLMs and need to assess how well they perform text retrieval tasks when faced with common typographical errors, homophones, or other subtle misspellings.

Not ideal if you are looking for a tool to correct typos in text or a general-purpose LLM evaluation framework that goes beyond spelling variations.

LLM evaluation natural language processing text analysis data quality AI model robustness
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 8 / 25
Community 5 / 25

How are scores calculated?

Stars

19

Forks

1

Language

Python

License

Last pushed

Mar 22, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/nlp/cx0/llm-typos"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.