Isaka-code/llm-20-questions
9th Place Solution - LLM 20 Questions
This project helps you accurately play a game of 20 Questions, acting as either the questioner or the answerer. It takes a secret keyword and a series of yes/no questions, then outputs precise answers or a series of optimal questions to identify the keyword. This is designed for anyone interested in building highly accurate, LLM-powered question-answering systems for games or specific classification tasks.
No commits in the last 6 months.
Use this if you want to understand how to build a robust system that can strategically ask questions or answer them based on a hidden keyword, combining rule-based logic, keyword matching, and LLM context.
Not ideal if you're looking for a general-purpose conversational AI chatbot or a tool to generate creative text without specific question-answering constraints.
Stars
10
Forks
1
Language
Python
License
MIT
Category
Last pushed
Aug 31, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/Isaka-code/llm-20-questions"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
GrapeCity-AI/gc-qa-rag
A RAG (Retrieval-Augmented Generation) solution Based on Advanced Pre-generated QA Pairs. 基于高级...
UKPLab/PeerQA
Code and Data for PeerQA: A Scientific Question Answering Dataset from Peer Reviews, NAACL 2025
Arfazrll/RAG-DocsInsight-Engine
Retrieval Augmented Generation (RAG) engine for intelligent document analysis. integrating LLM,...
faerber-lab/SQuAI
SQuAI: Scientific Question-Answering with Multi-Agent Retrieval-Augmented Generation (CIKM'25)
Vbj1808/Dokis
Lightweight RAG provenance middleware. Verifies every claim in an LLM response is grounded in a...