wzy6642/I3C-Select
Official implementation for "Instructing Large Language Models to Identify and Ignore Irrelevant Conditions" (NAACL 2024)
This project helps large language models (LLMs) solve complex problems more accurately by identifying and ignoring unnecessary information. It takes in a problem, such as a math word problem, and generates a more focused version, enabling the LLM to produce a correct answer. Anyone who uses or develops applications relying on LLMs for problem-solving can benefit from this.
No commits in the last 6 months.
Use this if you need LLMs to consistently disregard irrelevant details within prompts to improve their problem-solving accuracy.
Not ideal if your problems contain only essential information and do not typically suffer from irrelevant or confusing conditions.
Stars
8
Forks
—
Language
Python
License
Apache-2.0
Category
Last pushed
May 25, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/prompt-engineering/wzy6642/I3C-Select"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Featured in
Higher-rated alternatives
microsoft/promptbench
A unified evaluation framework for large language models
uptrain-ai/uptrain
UpTrain is an open-source unified platform to evaluate and improve Generative AI applications....
levitation-opensource/Manipulative-Expression-Recognition
MER is a software that identifies and highlights manipulative communication in text from human...
microsoftarchive/promptbench
A unified evaluation framework for large language models
gabe-mousa/Apolien
AI Safety Evaluation Library