Theory of Mind May Have Spontaneously Emerged in Large Language Models | Hacker News
What is being demonstrated in the article is that given billions of tokens of human-written training data, a statistical model can generate text that satisfies some of our expectations of how a person would respond to this task. Essentially we have enough parameters to capture from existing writing that statistically, the most likely word following "she looked in the bag labelled (X), and saw that it was full of (NOT X). She felt " is "surprised" or "confused" or some other word that is commonly embedded alongside contradictions. What this article is not showing (but either irresponsibly or naively suggests) is that the LLM knows what a bag is, what a person is, what popcorn and chocolate are, and can then put itself in the shoes of someone experiencing this situation, and finally communicate its own theory of what is going on in that person's mind. That is just not in evidence. The discussion is also muddled, saying that if structural properties of language create the ability to solve
This highlights one of the types of muddled thinking around LLMs. These tasks are used to test theory of mind because for people, language is a reliable representation of what type of thoughts are going on in the person's mind. In the case of an LLM the language generated doesn't have the same relationship to reality as it does for a person. What is being demonstrated in the article is that given billions of tokens of human-written training data, a statistical model can generate text that satisfies some of our expectations of how a person would respond to this task. Essentially we have…
related reading
- Do large language models understand us? | by Blaise Aguera y Arcas | Mediummedium.com
- [2302.02083] Theory of Mind May Have Spontaneously Emerged in Large Language Modelsarxiv.org
- Tracing the thoughts of a large language model \ Anthropicanthropic.com
- trees are harlequins, words are harlequins - the voidnostalgebraist.tumblr.com
- [2302.02083] Evaluating Large Language Models in Theory of Mind Tasksarxiv.org
- Large Language Model: world models or surface statistics?thegradient.pub
- LLM Daydreaming · Gwern.netgwern.net
- The Unintelligibility is Ours: Notes on Chain of Thought1a3orn.com
- Against LLM Reductionism — LessWronglesswrong.com
- Are Large Language Models Conscious?noemamag.com
- Against LLM Reductionismerichgrunewald.com
- Language Models in Plato's Cave - by Sergey Levinesergeylevine.substack.com