PAL (Program-Aided Language Models)

Gao et al., (2022) presents a method that uses LLMs to read natural language problems and generate programs as the intermediate reasoning steps. Coined, program-aided language models (PAL), it differs from chain-of-thought prompting in that instead of using free-form text to obtain solution it offloads the solution step to a programmatic runtime such as a Python interpreter.

Image Source: Gao et al., (2022)

Let's look at an example using LangChain and OpenAI GPT-3. We are interested to develop a simple application that's able to interpret the question being asked and provide an answer by leveraging the Python interpreter.

Specifically, we are interested to create a functionality that allows the use of the LLM to answer questions that require date understanding. We will provide the LLM a prompt that includes a few exemplars which are adopted from here.

These are the imports we need:

import openaifrom datetime import datetimefrom dateutil.relativedelta import relativedeltaimport osfrom langchain.llms import OpenAIfrom dotenv import load_dotenv

Let's first configure a few things:

load_dotenv() # API configurationopenai.api_key = os.getenv("OPENAI_API_KEY") # for LangChainos.environ["OPENAI_API_KEY"] = os.getenv("OPENAI_API_KEY")

Setup model instance:

llm = OpenAI(model_name='text-davinci-003', temperature=0)

Setup prompt + question:

question = "Today is 27 February 2023. I was born exactly 25 years ago. What is the date I was born in MM/DD/YYYY?" DATE_UNDERSTANDING_PROMPT = """# Q: 2015 is coming in 36 hours. What is the date one week from today in MM/DD/YYYY?# If 2015 is coming in 36 hours, then today is 36 hours before.today = datetime(2015, 1, 1) - relativedelta(hours=36)# One week from today,one_week_from_today = today + relativedelta(weeks=1)# The answer formatted with %m/%d/%Y isone_week_from_today.strftime('%m/%d/%Y')# Q: The first day of 2019 is a Tuesday, and today is the first Monday of 2019. What is the date today in MM/DD/YYYY?# If the first day of 2019 is a Tuesday, and today is the first Monday of 2019, then today is 6 days later.today = datetime(2019, 1, 1) + relativedelta(days=6)# The answer formatted with %m/%d/%Y istoday.strftime('%m/%d/%Y')# Q: The concert was scheduled to be on 06/01/1943, but was delayed by one day to today. What is the date 10 days ago in MM/DD/YYYY?# If the concert was scheduled to be on 06/01/1943, but was delayed by one day to today, then today is one day later.today = datetime(1943, 6, 1) + relativedelta(days=1)# 10 days ago,ten_days_ago = today - relativedelta(days=10)# The answer formatted with %m/%d/%Y isten_days_ago.strftime('%m/%d/%Y')# Q: It is 4/19/1969 today. What is the date 24 hours later in MM/DD/YYYY?# It is 4/19/1969 today.today = datetime(1969, 4, 19)# 24 hours later,later = today + relativedelta(hours=24)# The answer formatted with %m/%d/%Y istoday.strftime('%m/%d/%Y')# Q: Jane thought today is 3/11/2002, but today is in fact Mar 12, which is 1 day later. What is the date 24 hours later in MM/DD/YYYY?# If Jane thought today is 3/11/2002, but today is in fact Mar 12, then today is 3/12/2002.today = datetime(2002, 3, 12)# 24 hours later,later = today + relativedelta(hours=24)# The answer formatted with %m/%d/%Y islater.strftime('%m/%d/%Y')# Q: Jane was born on the last day of Feburary in 2001. Today is her 16-year-old birthday. What is the date yesterday in MM/DD/YYYY?# If Jane was born on the last day of Feburary in 2001 and today is her 16-year-old birthday, then today is 16 years later.today = datetime(2001, 2, 28) + relativedelta(years=16)# Yesterday,yesterday = today - relativedelta(days=1)# The answer formatted with %m/%d/%Y isyesterday.strftime('%m/%d/%Y')# Q: {question}""".strip() + '\n'

llm_out = llm(DATE_UNDERSTANDING_PROMPT.format(question=question))print(llm_out)

This will output the following:

# If today is 27 February 2023 and I was born exactly 25 years ago, then I was born 25 years before.today = datetime(2023, 2, 27)# I was born 25 years before,born = today - relativedelta(years=25)# The answer formatted with %m/%d/%Y isborn.strftime('%m/%d/%Y')

The contents of llm_out are a Python code snippet. Below, the exec command is used to execute this Python code snippet.

exec(llm_out)print(born)

This will output the following: 02/27/1998