UKPLab/emnlp2024-code-prompting
Code Prompting Elicits Conditional Reasoning Abilities in Text+Code LLMs. EMNLP 2024
This project helps AI/ML researchers and practitioners explore how using code-based prompts can improve the conditional reasoning abilities of Large Language Models (LLMs). It takes natural language problems and transforms them into code, which is then fed to the LLM. The output helps understand if code prompts lead to more accurate answers and better tracking of entities compared to traditional text-based prompts.
No commits in the last 6 months.
Use this if you are a researcher or developer working with LLMs and want to evaluate or improve their ability to handle complex conditional logic and scenario-based question answering.
Not ideal if you are looking for a ready-to-use application or a production-grade solution for end-user natural language processing tasks.
Stars
27
Forks
4
Language
Python
License
Apache-2.0
Category
Last pushed
Nov 13, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/prompt-engineering/UKPLab/emnlp2024-code-prompting"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
meta-prompting/meta-prompting
Official implementation of Meta Prompting for AI Systems (https://arxiv.org/abs/2311.11482)
auniquesun/Point-PRC
[NeurIPS 2024] Official implementation of the paper "Point-PRC: A Prompt Learning Based...
slashrebootofficial/simulated-metacognition-in-open-source-llms
This repository archives artifacts (prompts, configs, logs, and scripts) from a series of...
egmaminta/GEPA-Lite
A lightweight implementation of the GEPA (Genetic-Pareto) prompt optimization method for large...
Techolution/LazyLM
A prompting framework for getting foundational models to “lazily” evaluate their reasoning trace