# Semantic features of object concepts generated with GPT-3

arXiv: https://arxiv.org/abs/2202.03753 · HTML: https://mlsanity.com/paper/2202.03753/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 33 references that are in the map.
- First posted on arXiv 8 Feb 2022.

## Builds on (most cited first, 11 of 11)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding](https://mlsanity.com/paper/1804.07461/) (2018)
- [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013)
- [Language Models as Knowledge Bases?](https://mlsanity.com/paper/1909.01066/) (2019)
- [COMET: Commonsense Transformers for Automatic Knowledge Graph Construction](https://mlsanity.com/paper/1906.05317/) (2019)
- [The Next Decade in AI: Four Steps Towards Robust Artificial Intelligence](https://mlsanity.com/paper/2002.06177/) (2020)
- [SimLex-999: Evaluating Semantic Models with (Genuine) Similarity Estimation](https://mlsanity.com/paper/1408.3456/) (2014)
- [SPINE: SParse Interpretable Neural Embeddings](https://mlsanity.com/paper/1711.08792/) (2017)
- [Semantic projection: recovering human knowledge of multiple, distinct object features from word embeddings](https://mlsanity.com/paper/1802.01241/) (2018)
- [Feature2Vec: Distributional semantic modelling of human property knowledge](https://mlsanity.com/paper/1908.11439/) (2019)

## Built on by (most cited first, 12 of 12)

- [Large Language Models: The Need for Nuance in Current Debates and a Pragmatic Perspective on Understanding](https://mlsanity.com/paper/2310.19671/) (2023)
- [Conceptual structure coheres in human cognition but not in large language models](https://mlsanity.com/paper/2304.02754/) (2023)
- [On the Tip of the Tongue: Analyzing Conceptual Representation in Large Language Models with Reverse-Dictionary Probe](https://mlsanity.com/paper/2402.14404/) (2024)
- [Can LLMs Simulate Human Behavioral Variability? A Case Study in the Phonemic Fluency Task](https://mlsanity.com/paper/2505.16164/) (2025)
- [Seeing What Tastes Good: Revisiting Multimodal Distributional Semantics in the Billion Parameter Era](https://mlsanity.com/paper/2506.03994/) (2025)
- [Human-machine cooperation for semantic feature listing](https://mlsanity.com/paper/2304.05012/) (2023)
- [AI-enhanced semantic feature norms for 786 concepts](https://mlsanity.com/paper/2505.10718/) (2025)
- [The language of sounds unheard: Exploring musical timbre semantics of large language models](https://mlsanity.com/paper/2304.07830/) (2023)
- [How Humans and LLMs Organize Conceptual Knowledge: Exploring Subordinate Categories in Italian](https://mlsanity.com/paper/2505.21301/) (2025)
- [Large Language Models estimate fine-grained human color-concept associations](https://mlsanity.com/paper/2406.17781/) (2024)
- [Large Language Models as a Tool for Mining Object Knowledge](https://mlsanity.com/paper/2410.12959/) (2024)
- [Comparing Semantic Navigation in Humans and Large Language Models using Natural Language Processing](https://mlsanity.com/paper/2607.12195/) (2026)

## Abstract (arXiv)

Semantic features have been playing a central role in investigating the nature of our conceptual representations. Yet the enormous time and effort required to empirically sample and norm features from human raters has restricted their use to a limited set of manually curated concepts. Given recent promising developments with transformer-based language models, here we asked whether it was possible to use such models to automatically generate meaningful lists of properties for arbitrary object concepts and whether these models would produce features similar to those found in humans. To this end, we probed a GPT-3 model to generate semantic features for 1,854 objects and compared automatically-generated features to existing human feature norms. GPT-3 generated many more features than humans, yet showed a similar distribution in the types of generated features. Generated feature norms rivaled human norms in predicting similarity, relatedness, and category membership, while variance partitioning demonstrated that these predictions were driven by similar variance in humans and GPT-3. Together, these results highlight the potential of large language models to capture important facets of human knowledge and yield a new approach for automatically generating interpretable feature sets, thus drastically expanding the potential use of semantic features in psychological and linguistic studies.