# Using large language models to estimate features of multi-word expressions: Concreteness, valence, arousal

arXiv: https://arxiv.org/abs/2408.16012 · HTML: https://mlsanity.com/paper/2408.16012/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 62 references that are in the map.
- First posted on arXiv 16 Aug 2024.

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

- [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013)
- [EPIE Dataset: A Corpus For Possible Idiomatic Expressions](https://mlsanity.com/paper/2006.09479/) (2020)
- [Learning and Evaluating Emotion Lexicons for 91 Languages](https://mlsanity.com/paper/2005.05672/) (2020)
- [How many words does ChatGPT know? The answer is ChatWords](https://mlsanity.com/paper/2309.16777/) (2023)
- [Establishing Vocabulary Tests as a Benchmark for Evaluating Large Language Models](https://mlsanity.com/paper/2310.14703/) (2023)

## Built on by (most cited first, 4 of 4)

- [Adding LLMs to the psycholinguistic norming toolbox: A practical guide to getting the most out of human ratings](https://mlsanity.com/paper/2509.14405/) (2025)
- [Social Perceptions of English Spelling Variation on Twitter: A Comparative Analysis of Human and LLM Responses](https://mlsanity.com/paper/2511.23041/) (2025)
- [Can GPT replace human raters? Validity and reliability of machine-generated norms for metaphors](https://mlsanity.com/paper/2512.12444/) (2025)
- [To Words and Beyond: Probing Large Language Models for Sentence-Level Psycholinguistic Norms of Memorability and Reading Times](https://mlsanity.com/paper/2603.12105/) (2026)

## Abstract (arXiv)

This study investigates the potential of large language models (LLMs) to provide accurate estimates of concreteness, valence and arousal for multi-word expressions. Unlike previous artificial intelligence (AI) methods, LLMs can capture the nuanced meanings of multi-word expressions. We systematically evaluated ChatGPT-4o's ability to predict concreteness, valence and arousal. In Study 1, ChatGPT-4o showed strong correlations with human concreteness ratings (r = .8) for multi-word expressions. In Study 2, these findings were repeated for valence and arousal ratings of individual words, matching or outperforming previous AI models. Study 3 extended the prevalence and arousal analysis to multi-word expressions and showed promising results despite the lack of large-scale human benchmarks. These findings highlight the potential of LLMs for generating valuable psycholinguistic data related to multiword expressions. To help researchers with stimulus selection, we provide datasets with AI norms of concreteness, valence and arousal for 126,397 English single words and 63,680 multi-word expressions