# Text Understanding in GPT-4 vs Humans

arXiv: https://arxiv.org/abs/2403.17196 · HTML: https://mlsanity.com/paper/2403.17196/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 26 references that are in the map.
- First posted on arXiv 25 Mar 2024.

## Builds on (most cited first, 5 of 5)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Sparks of Artificial General Intelligence: Early experiments with GPT-4](https://mlsanity.com/paper/2303.12712/) (2023)
- [Using cognitive psychology to understand GPT-3](https://mlsanity.com/paper/2206.14576/) (2022)
- [Mathematical Capabilities of ChatGPT](https://mlsanity.com/paper/2301.13867/) (2023)
- [Emergent Analogical Reasoning in Large Language Models](https://mlsanity.com/paper/2212.09196/) (2022)

## Built on by (most cited first, 1 of 1)

- [Safety from Honesty in a Disinterested AI Predictor](https://mlsanity.com/paper/2606.29657/) (2026)

## Abstract (arXiv)

We examine whether a leading AI system GPT4 understands text as well as humans do, first using a well-established standardized test of discourse comprehension. On this test, GPT4 performs slightly, but not statistically significantly, better than humans given the very high level of human performance. Both GPT4 and humans make correct inferences about information that is not explicitly stated in the text, a critical test of understanding. Next, we use more difficult passages to determine whether that could allow larger differences between GPT4 and humans. GPT4 does considerably better on this more difficult text than do the high school and university students for whom these the text passages are designed, as admission tests of student reading comprehension. Deeper exploration of GPT4 performance on material from one of these admission tests reveals generally accepted signatures of genuine understanding, namely generalization and inference.