wzy6642/I3C-Select

Official implementation for "Instructing Large Language Models to Identify and Ignore Irrelevant Conditions" (NAACL 2024)

20
/ 100
Experimental

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.

LLM problem-solving AI accuracy prompt engineering natural language understanding computational linguistics
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 4 / 25
Maturity 16 / 25
Community 0 / 25

How are scores calculated?

Stars

8

Forks

Language

Python

License

Apache-2.0

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.