When humans write sentences or solve math problems, they are thinking symbolically — each number, variable, or word is expressed by a symbol. While AI chatbots do not “think” that way, if prompted, they can offer cogent advice about writing, math, and many other topics just as a human would.
How artificial intelligence (AI) systems can do this is poorly understood because they are not directly programmed by humans. Instead, they are trained to develop their own internal strategies by analyzing massive amounts of data. And while use of AI chatbots will become increasingly common, the fact that people do not fully understand how they operate internally makes them difficult to trust — especially in sensitive situations.
A new study led by Yale computational linguist Tom McCoy provides insight into how large language models (LLMs) — the AI systems trained on large datasets to generate human-like texts — can ably perform tasks, like solving math problems or writing computer code, that appear to require symbolic reasoning. The study provides evidence that the internal representations of neural networks implicitly realize symbolic structure.
To read more, click here.