zlacker

>>koie+(OP)
Hmm. I quickly made up an example of a logical fallacy and asked GPT-4 about it. Seemed to do a pretty good job, to me.

> All apples are red. All apples are fruit. My car is red, therefore my car is a fruit. Find the logical error

-----

The logical error in the statement "All apples are red. All apples are fruit. My car is red, therefore my car is a fruit." is a classic example of the fallacy of the undistributed middle. This fallacy occurs when a syllogism (a form of reasoning in which a conclusion is drawn from two given or assumed propositions) is improperly formed because the middle term is not distributed at least once in the premises.

Here's a breakdown of the fallacy in your statement:

Major Premise: All apples are fruit. Minor Premise: All apples are red. Conclusion: My car is red, therefore my car is a fruit. In this syllogism, "apples" is the middle term. However, it is not distributed correctly. The major premise talks about all apples being fruits, and the minor premise talks about all apples being red. However, there's no premise that states all things that are red are apples. Without this, you cannot logically conclude that other red things, like a car, are fruits.

In simpler terms, just because all apples are red and fruits, it doesn't mean that all red things are fruits. The color of the apples (red) is not an exclusive property that defines the category of fruits. Your car shares the property of being red with apples, but it doesn't share the essential property of being a fruit.

>>Ragnar+1O
You said "Find the logical error", meaning you told it the logical error is there. That doesn't show the model can find errors when it isn't told that the error is there.

Your post shows how the model can correct a reasoning error. That is different from finding an error when it isn't pointed out, that is why he title to this post is "LLMs cannot find reasoning errors, but can correct them". You using the phrasing "find the logical error" doesn't contradict the title.

>>Jensso+ZS
> All apples are red. All apples are fruit. My car is red, therefore my car is a fruit.

> The conclusion "My car is a fruit" is not logically valid. This is an example of the fallacy of the undistributed middle. The logic goes as follows:

1. All apples are red. (Premise)

2. All apples are fruit. (Premise)

3. My car is red. (Premise)

4. Therefore, my car is a fruit. (Conclusion)

The fallacy arises because the premises do not establish a shared property between "red things" and "fruit" in a way that would include the car. Just because both apples and the car share the property of being red, it does not mean they share all properties of apples, such as being a fruit.

>>kaoD+2U
> All apples are red. All apples are fruit. My car is red, therefore my car is a fruit.

I Googled that exact phrase and got solutions. A logical problem that can be solved by a search engine isn't a valid example, the LLM knows that it is a logical puzzle just by how you phrased it just like Google knows that it is a logical puzzle.

And no, doing tiny alterations to that until you no longer get any Google hits isn't a proof ChatGPT can do logic, it is proof that ChatGPT can parse general structure and find patterns better than a search engine can. You need to do logical problems that can't easily be translated to standard problems that there are tons of examples of in the wild.

>>Jensso+D11
> And no, doing tiny alterations to that until you no longer get any Google hits isn't a proof ChatGPT can do logic

Can you show "the" implementation of "can do logic"?

Is it possible to demonstrate that it can do logic?