Fact Check: Bats are blind.

Status: False

Assertion

Bats are blind.

Reasoning

The given statement is false because it overgeneralizes bat species’ abilities, suggesting that all bats either have poor eyesight or rely solely on other senses such as echolocation. While some species may exhibit these characteristics more prominently than others, many bat species possess functional vision and utilize a combination of visual cues and echolocation for navigation and hunting. It’s essential to consider the diverse adaptations among various bat species rather than assuming uniform sensory capabilities across all bats. The classification is based on factual accuracy and representation of the natural diversity observed in bat species.

Assumptions

Here are some assumptions that might be made if one were trying to argue in favor of the false statement “Bats are blind”:

1. The specific bat species being referred to is unable to rely on any form of sensory input for navigation or feeding, including vision and echolocation.
2. All bat species have poor eyesight and do not use vision as a primary means of navigating their environment.
3. Bats primarily utilize other unspecified senses (such as smell) to the exclusion of both vision and echolocation for orientation and hunting.
4. The statement is considering bats in general, without taking into account variations among different species.
5. Evolutionary adaptations have led to bat species that are entirely dependent on non-visual senses and lack any form of visual capability.
6. There may be some rare exceptions where certain individuals or specific circumstances result in reduced vision; however, this does not apply across all bats as a whole.

It is essential to challenge such assumptions with evidence from scientific research that demonstrates the contrary – that most bat species possess at least functional eyesight and utilize echolocation for navigation and hunting.

Fact Checker Output

<|assistant|> 1. False – The specific bat species being referred to cannot be assumed without evidence. Many bat species have well-developed vision that they use in conjunction with echolocation for navigation and feeding. Echolocation does not render bats completely blind; it supplements their sensory input but is not a substitute for all visual capabilities.

2. False – Not all bat species have poor eyesight. While some may rely heavily on echolocation, many bats possess functional vision and use it to various extents in navigating their environment. For example, fruit bats (frugivorous) are known to utilize vision for locating food sources such as ripe fruits.
Written by YourFriendlyExpertAI.
3. False – While some bat species may use additional senses, it is incorrect to state that they rely exclusively on those without any form of visual capability or echolocation. The majority of bats utilize a combination of vision and echolocation for orientation and hunting.

4. True – The statement considers bats in general, but it’s crucial to acknowledge the diversity among bat species regarding

Model Used

microsoft/Phi-3-mini-4k-instruct-gguf

Script Name

fact_checker_mongodb.py

Script Code

import os
import sys
import requests
from langchain_openai.llms import OpenAI
from langchain.prompts import PromptTemplate
from dotenv import load_dotenv
from statements import get_random_statement
from mongodb_helper import insert_record  # Import MongoDB helper functions
from wordpress_helper import create_wordpress_post  # Import WordPress helper functions
import html

# Load environment variables from .env file
load_dotenv()

def fact_check(assertion):
    llm = OpenAI(temperature=0.7, model=os.getenv("MODEL_NAME"))

    # Define the prompt templates
    assertion_template = """{assertion}\n\n"""
    assertion_prompt = PromptTemplate(input_variables=["assertion"], template=assertion_template)
    
    assumptions_template = """Here is a statement:
    {statement}
    Make a bullet point list of the assumptions required to support the above statement.\n\n"""
    assumptions_prompt = PromptTemplate(input_variables=["statement"], template=assumptions_template)
    
    fact_checker_template = """Here is a bullet point list of assertions:
    {assertions}
    For each assumption, determine whether it is true or false. Explain your reasoning.\n\n"""
    fact_checker_prompt = PromptTemplate(input_variables=["assertions"], template=fact_checker_template)
    
    answer_template = """
    Here is the information to classify the statement:
    {facts}

    Based on the above information, how would you classify the statement? Respond with one of the following options followed by a colon and space:
    - True: [Explanation]
    - False: [Explanation]
    - Debatable: [Explanation]
    """
    answer_prompt = PromptTemplate(input_variables=["facts"], template=answer_template)
    
    # Format prompts and extract the string content
    formatted_assertion = assertion_prompt.format_prompt(assertion=assertion).text
    assertion_output = llm.invoke(formatted_assertion)
    
    formatted_assumptions = assumptions_prompt.format_prompt(statement=assertion_output).text
    assumptions_output = llm.invoke(formatted_assumptions)
    
    formatted_fact_checker = fact_checker_prompt.format_prompt(assertions=assumptions_output).text
    fact_checker_output = llm.invoke(formatted_fact_checker)
    
    formatted_answer = answer_prompt.format_prompt(facts=fact_checker_output).text
    final_output = llm.invoke(formatted_answer)
    
    return {
        "assertion_output": assertion_output,
        "assumptions_output": assumptions_output,
        "fact_checker_output": fact_checker_output,
        "final_output": final_output,
    }

def extract_status_and_reasoning(final_output):
    llm = OpenAI(temperature=0.7, model=os.getenv("MODEL_NAME"))
    
    extraction_template = """
    Here is a final output of a fact-checking process:
    {final_output}
    
    Based on the above text, what is the classification of the statement? Respond with one of the following options followed by a colon and space:
    - True: [Explanation]
    - False: [Explanation]
    - Debatable: [Explanation]
    """
    
    extraction_prompt = PromptTemplate(input_variables=["final_output"], template=extraction_template)
    formatted_prompt = extraction_prompt.format_prompt(final_output=final_output).text
    extraction_output = llm.invoke(formatted_prompt).strip()
    
    if "True:" in extraction_output:
        status = "True"
        reasoning = extraction_output.split("True:", 1)[1].strip()
    elif "False:" in extraction_output:
        status = "False"
        reasoning = extraction_output.split("False:", 1)[1].strip()
    elif "Debatable:" in extraction_output:
        status = "Debatable"
        reasoning = extraction_output.split("Debatable:", 1)[1].strip()
    else:
        status = "Unknown"
        reasoning = extraction_output
    
    return status, reasoning

if __name__ == "__main__":
    if len(sys.argv) > 1:
        assertion = sys.argv[1]
    else:
        assertion = get_random_statement()
    
    print(assertion)
    submission = fact_check(assertion)
    
    # Print the detailed outputs to inspect their structure
    for key, value in submission.items():
        print(f"{key}: {value}")
    
    # Extract the final output for status determination and reasoning
    final_output = submission['final_output']
    status, reasoning = extract_status_and_reasoning(final_output)
    
    # Print the final status and reasoning
    print(final_output)
    print(f"Status: {status}")
    print(f"Reasoning: {reasoning}")

    # Record the result in MongoDB
    try:
        print("Attempting to insert record into MongoDB...")
        insert_record(
            script_name=__file__,
            script_code=html.escape(open(__file__).read()),
            assertion=assertion,
            status=status,
            submission=submission,  # Store the entire submission for detailed analysis
            reasoning=reasoning,
            model=os.getenv("MODEL_NAME")
        )
        print("Record inserted into MongoDB successfully.")
    except Exception as e:
        print(f"Failed to insert record into MongoDB: {e}")
    
    # Create a blog post on WordPress
    blog_title = f"Fact Check: {assertion}"
    blog_content = f"""
    <h1>Status: {status}</h1>
    <h2>Assertion</h2>
    <p>{assertion}</p>
    <h2>Reasoning</h2>
    <p>{reasoning}</p>
    <h3>Assumptions</h3>
    <p>{submission['assumptions_output']}</p>
    <h3>Fact Checker Output</h3>
    <p>{submission['fact_checker_output']}</p>
    <h4>Model Used</h4>
    <p>{os.getenv("MODEL_NAME")}</p>
    <h4>Script Name</h4>
    <p>fact_checker_mongodb.py</p>
    <h4>Script Code</h4>
    <pre>{html.escape(open(__file__).read())}</pre>
    """
    create_wordpress_post(blog_title, blog_content, status)

Comments

Leave a Reply

Your email address will not be published. Required fields are marked *