AI-enhanced semantic feature norms for 786 concepts
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910947208069120 |
|---|---|
| author | Suresh, Siddharth Mukherjee, Kushin Giallanza, Tyler Yu, Xizheng Patil, Mia Cohen, Jonathan D. Rogers, Timothy T. |
| author_facet | Suresh, Siddharth Mukherjee, Kushin Giallanza, Tyler Yu, Xizheng Patil, Mia Cohen, Jonathan D. Rogers, Timothy T. |
| contents | Semantic feature norms have been foundational in the study of human conceptual knowledge, yet traditional methods face trade-offs between concept/feature coverage and verifiability of quality due to the labor-intensive nature of norming studies. Here, we introduce a novel approach that augments a dataset of human-generated feature norms with responses from large language models (LLMs) while verifying the quality of norms against reliable human judgments. We find that our AI-enhanced feature norm dataset, NOVA: Norms Optimized Via AI, shows much higher feature density and overlap among concepts while outperforming a comparable human-only norm dataset and word-embedding models in predicting people's semantic similarity judgments. Taken together, we demonstrate that human conceptual knowledge is richer than captured in previous norm datasets and show that, with proper validation, LLMs can serve as powerful tools for cognitive science research. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_10718 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | AI-enhanced semantic feature norms for 786 concepts Suresh, Siddharth Mukherjee, Kushin Giallanza, Tyler Yu, Xizheng Patil, Mia Cohen, Jonathan D. Rogers, Timothy T. Computation and Language Artificial Intelligence Human-Computer Interaction Semantic feature norms have been foundational in the study of human conceptual knowledge, yet traditional methods face trade-offs between concept/feature coverage and verifiability of quality due to the labor-intensive nature of norming studies. Here, we introduce a novel approach that augments a dataset of human-generated feature norms with responses from large language models (LLMs) while verifying the quality of norms against reliable human judgments. We find that our AI-enhanced feature norm dataset, NOVA: Norms Optimized Via AI, shows much higher feature density and overlap among concepts while outperforming a comparable human-only norm dataset and word-embedding models in predicting people's semantic similarity judgments. Taken together, we demonstrate that human conceptual knowledge is richer than captured in previous norm datasets and show that, with proper validation, LLMs can serve as powerful tools for cognitive science research. |
| title | AI-enhanced semantic feature norms for 786 concepts |
| topic | Computation and Language Artificial Intelligence Human-Computer Interaction |
| url | https://arxiv.org/abs/2505.10718 |