In this repo, we (Kaushik, Pulkit and Vitaly) attempt to come up with a hopefully brand new prompting approach called cluster prompt. This is part of our course work for the IFT 6165 class at MILA, taught by Dr. Irina Rish. A report detailing our findings is available at this link.
The rest of this README.md is forked from PAL by Gao et. al. We try to build on top of their work and stand on the shoulders of giants in our work.
Setup your OpenAI key as an environment variable called: OPENAI_API_KEY (variable name), the variable value will be your API key.
Clone this repo and install with pip
.
git clone https://github.com/Etrama/PAL_v2.git
pip install -e ./pal
Before running the scripts, set the OpenAI key,
export OPENAI_API_KEY='sk-...'
The core components of the pal
package are the Interface classes. Specifically, ProgramInterface
connects the LLM backend, a Python backend and user prompts.
import pal
from pal.prompt import math_prompts
interface = pal.interface.ProgramInterface(
model='code-davinci-002',
stop='\n\n\n', # stop generation str for Codex API
get_answer_expr='solution()' # python expression evaluated after generated code to obtain answer
)
question = 'xxxxx'
prompt = math_prompts.MATH_PROMPT.format(question=question)
answer = interface.run(prompt)
Here, the interface
's run
method will run generation with the OpenAI API, run the generated snippet and then evaluate get_answer_expr
(here solution()
) to obtain the final answer.
User should set get_answer_expr
based on the prompt.
We provide simple inference loops in the scripts/
folder.
mkdir eval_results
python scripts/{colored_objects|gsm|date_understanding|penguin}_eval.py
We have a beta release of a ChatGPT dedicated script for math reasoning.
python scripts/gsm_chatgpt.py
For running bulk inference, we used the generic prompting library prompt-lib and recommend it for running CoT inferenence on all tasks used in our work.
For the complete details of the results, see the paper .
@article{gao2022pal,
title={PAL: Program-aided Language Models},
author={Gao, Luyu and Madaan, Aman and Zhou, Shuyan and Alon, Uri and Liu, Pengfei and Yang, Yiming and Callan, Jamie and Neubig, Graham},
journal={arXiv preprint arXiv:2211.10435},
year={2022}
}