# Semantic Change Characterization with LLMs using Rhetorics

arXiv: https://arxiv.org/abs/2407.16624 · HTML: https://mlsanity.com/paper/2407.16624/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 52 references that are in the map.
- First posted on arXiv 23 Jul 2024.

## Builds on (most cited first, 20 of 20)

- [Language Models as Knowledge Bases?](https://mlsanity.com/paper/1909.01066/) (2019)
- [The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A"](https://mlsanity.com/paper/2309.12288/) (2023)
- [WiC: the Word-in-Context Dataset for Evaluating Context-Sensitive Meaning Representations](https://mlsanity.com/paper/1808.09121/) (2018)
- [Emergent Analogical Reasoning in Large Language Models](https://mlsanity.com/paper/2212.09196/) (2022)
- [Language models show human-like content effects on reasoning tasks](https://mlsanity.com/paper/2207.07051/) (2022)
- [The Unreliability of Explanations in Few-shot Prompting for Textual Reasoning](https://mlsanity.com/paper/2205.03401/) (2022)
- [Orca 2: Teaching Small Language Models How to Reason](https://mlsanity.com/paper/2311.11045/) (2023)
- [SemEval-2020 Task 1: Unsupervised Lexical Semantic Change Detection](https://mlsanity.com/paper/2007.11464/) (2020)
- [Testing the Ability of Language Models to Interpret Figurative Language](https://mlsanity.com/paper/2204.12632/) (2022)
- [Survey of Computational Approaches to Lexical Semantic Change](https://mlsanity.com/paper/1811.06278/) (2018)
- [MelBERT: Metaphor Detection via Contextualized Late Interaction using Metaphorical Identification Theories](https://mlsanity.com/paper/2104.13615/) (2021)
- [Exploring the Potential of Large Language Models in Computational Argumentation](https://mlsanity.com/paper/2311.09022/) (2023)
- [Interpretable Word Sense Representations via Definition Generation: The Case of Semantic Change Analysis](https://mlsanity.com/paper/2305.11993/) (2023)
- [Challenges for Computational Lexical Semantic Change](https://mlsanity.com/paper/2101.07668/) (2021)
- [Using Synchronic Definitions and Semantic Relations to Classify Semantic Change Types](https://mlsanity.com/paper/2406.03452/) (2024)
- [The DURel Annotation Tool: Human and Computational Measurement of Semantic Proximity, Sense Clusters and Semantic Change](https://mlsanity.com/paper/2311.12664/) (2023)
- [Analyzing Semantic Change through Lexical Replacements](https://mlsanity.com/paper/2404.18570/) (2024)
- [Metaphorical Polysemy Detection: Conventional Metaphor meets Word Sense Disambiguation](https://mlsanity.com/paper/2212.08395/) (2022)
- [Survey in Characterizing Semantic Change](https://mlsanity.com/paper/2402.19088/) (2024)
- [Large Language Models on Lexical Semantic Change Detection: An Evaluation](https://mlsanity.com/paper/2312.06002/) (2023)

## Built on by (most cited first, 5 of 5)

- [Bias in Large Language Models: Origin, Evaluation, and Mitigation](https://mlsanity.com/paper/2411.10915/) (2024)
- [Simulating a Bias Mitigation Scenario in Large Language Models](https://mlsanity.com/paper/2509.14438/) (2025)
- [LSC-Eval: A General Framework to Evaluate Methods for Assessing Dimensions of Lexical Semantic Change Using LLM-Generated Synthetic Data](https://mlsanity.com/paper/2503.08042/) (2025)
- [Relation Geometry in Semantic Space of Language Models](https://mlsanity.com/paper/2607.26762/) (2026)
- [Lexical Redefinition Reveals Context-Sensitive Instruction Following](https://mlsanity.com/paper/2610.16952/) (2026)

## Abstract (arXiv)

Languages continually evolve in response to societal events, resulting in new terms and shifts in meanings. These changes have significant implications for computer applications, including automatic translation and chatbots, making it essential to characterize them accurately. The recent development of LLMs has notably advanced natural language understanding, particularly in sense inference and reasoning. In this paper, we investigate the potential of LLMs in characterizing three types of semantic change: dimension, relation, and orientation. We achieve this by combining LLMs' Chain-of-Thought with rhetorical devices and conducting an experimental assessment of our approach using newly created datasets. Our results highlight the effectiveness of LLMs in capturing and analyzing semantic changes, providing valuable insights to improve computational linguistic applications.