hongbinye/Cognitive-Mirage-Hallucinations-in-LLMs

Repository for the paper "Cognitive Mirage: A Review of Hallucinations in Large Language Models"

29
/ 100
Experimental

This project provides a comprehensive overview of how Large Language Models (LLMs) can generate incorrect or misleading information, known as "hallucinations." It takes in various research papers and existing LLM models, categorizes the types of hallucinations, and outlines methods for detecting and improving LLM reliability. It's designed for researchers, AI developers, and technical practitioners working with or building on LLMs.

No commits in the last 6 months.

Use this if you need to understand the underlying causes and solutions for inaccurate outputs from Large Language Models and want to explore research-backed strategies for mitigation.

Not ideal if you are a non-technical user looking for a simple tool to instantly fix LLM hallucinations without engaging with research or technical concepts.

AI safety LLM reliability natural language processing AI research machine learning engineering
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 5 / 25

How are scores calculated?

Stars

49

Forks

2

Language

License

MIT

Last pushed

Oct 21, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/hongbinye/Cognitive-Mirage-Hallucinations-in-LLMs"

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