Yup, (something like) the human anchor seems surprisingly good as a predictive model when interacting with LLMs. Related, especially for prompting: Large Language Models Are Implicitly Topic Models: Explaining and Finding Good Demonstrations for In-Context Learning; A fine-grained comparison of pragmatic language understanding in humans and language models; Task Ambiguity in Humans and Language Models.
Yup, (something like) the human anchor seems surprisingly good as a predictive model when interacting with LLMs. Related, especially for prompting: Large Language Models Are Implicitly Topic Models: Explaining and Finding Good Demonstrations for In-Context Learning; A fine-grained comparison of pragmatic language understanding in humans and language models; Task Ambiguity in Humans and Language Models.