Papers by Wei-Chun Huang
Conceptual structure coheres in human cognition but not in large language models (2023.emnlp-main)
Copied to clipboard
| Challenge: | Neural network models of language have long been used to develop hypotheses about conceptual representation in the mind and brain. |
| Approach: | They propose to use three techniques borrowed from cognitive psychology to estimate lexical-semantic structure in humans and a large language model. |
| Outcome: | The proposed models show that human-like models can estimate lexical-semantic structure robustly to cultural, language, and method of estimation. |