# Word Definitions from Large Language Models

arXiv: https://arxiv.org/abs/2311.06362 · HTML: https://mlsanity.com/paper/2311.06362/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 68 references that are in the map.
- First posted on arXiv 10 Nov 2023.

## Builds on (most cited first, 21 of 21)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013)
- [Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing](https://mlsanity.com/paper/2107.13586/) (2021)
- [Enriching Word Vectors with Subword Information](https://mlsanity.com/paper/1607.04606/) (2016)
- [MPNet: Masked and Permuted Pre-training for Language Understanding](https://mlsanity.com/paper/2004.09297/) (2020)
- [Dynamic Routing Between Capsules](https://mlsanity.com/paper/1710.09829/) (2017)
- [Large Language Models Are State-of-the-Art Evaluators of Translation Quality](https://mlsanity.com/paper/2302.14520/) (2023)
- [Can ChatGPT Assess Human Personalities? A General Evaluation Framework](https://mlsanity.com/paper/2303.01248/) (2023)
- [PEARL: Prompting Large Language Models to Plan and Execute Actions Over Long Documents](https://mlsanity.com/paper/2305.14564/) (2023)
- [A Multimodal Transformer: Fusing Clinical Notes with Structured EHR Data for Interpretable In-Hospital Mortality Prediction](https://mlsanity.com/paper/2208.10240/) (2022)
- [Definition Modeling: Learning to define word embeddings in natural language](https://mlsanity.com/paper/1612.00394/) (2016)
- [Will ChatGPT get you caught? Rethinking of Plagiarism Detection](https://mlsanity.com/paper/2302.04335/) (2023)
- [Hierarchical Prompting Assists Large Language Model on Web Navigation](https://mlsanity.com/paper/2305.14257/) (2023)
- [MultiTool-CoT: GPT-3 Can Use Multiple External Tools with Chain of Thought Prompting](https://mlsanity.com/paper/2305.16896/) (2023)
- [Paraphrase Identification with Deep Learning: A Review of Datasets and Methods](https://mlsanity.com/paper/2212.06933/) (2022)
- [BotTriNet: A Unified and Efficient Embedding for Social Bots Detection via Metric Learning](https://mlsanity.com/paper/2304.03144/) (2023)
- [Testing of Support Tools for Plagiarism Detection](https://mlsanity.com/paper/2002.04279/) (2020)
- [FineEHR: Refine Clinical Note Representations to Improve Mortality Prediction](https://mlsanity.com/paper/2304.11794/) (2023)
- [Analyzing Temporal Relationships between Trending Terms on Twitter and Urban Dictionary Activity](https://mlsanity.com/paper/2005.07655/) (2020)

## Abstract (arXiv)

Dictionary definitions are historically the arbitrator of what words mean, but this primacy has come under threat by recent progress in NLP, including word embeddings and generative models like ChatGPT. We present an exploratory study of the degree of alignment between word definitions from classical dictionaries and these newer computational artifacts. Specifically, we compare definitions from three published dictionaries to those generated from variants of ChatGPT. We show that (i) definitions from different traditional dictionaries exhibit more surface form similarity than do model-generated definitions, (ii) that the ChatGPT definitions are highly accurate, comparable to traditional dictionaries, and (iii) ChatGPT-based embedding definitions retain their accuracy even on low frequency words, much better than GloVE and FastText word embeddings.