Metaphor is a pervasive feature of discourse and a powerful lens for examining cognition, emotion, and ideology. Large-scale analysis, however, has been constrained by the need for manual annotation due to the context-sensitive nature of metaphor. This study investigates the potential of large language models (LLMs) to automate metaphor identification in full texts. We compare three methods: (i) retrieval-augmented generation (RAG), where the model is provided with a codebook and instructed to annotate texts based on its rules and examples; (ii) prompt engineering, where we design task-specific verbal instructions; and (iii) fine-tuning, where the model is trained on hand-coded texts to optimize performance. Within prompt engineering, we test zero-shot, few-shot, and chain-of-thought strategies. Our results show that state-of-the-art closed-source LLMs can achieve high accuracy, with fine-tuning yielding a median F1 score of 0.79. A comparison of human and LLM outputs reveals that most discrepancies are systematic, reflecting well-known grey areas and conceptual challenges in metaphor theory. We propose that LLMs can be used to at least partly automate metaphor identification and can serve as a testbed for developing and refining metaphor identification protocols and the theory that underpins them.

This note explores the innovative application of soliton theory and plasmonic phenomena in modeling user behavior and engagement within digital health platforms. By introducing the concept of soliton solutions, we present a novel approach to understanding stable patterns of health improvement behaviors over time. Additionally, we delve into the role of tellurium nanoparticles and their plasmonic properties in adsorbing fake news, thereby influencing user interactions and engagement levels. Through a theoretical framework that combines nonlinear dynamics with the unique characteristics of tellurium nanoparticles, we aim to provide new insights into the dynamics of user engagement in digital health environments. Our analysis highlights the potential of soliton theory in capturing the complex, nonlinear dynamics of user behavior, while the application of plasmonic phenomena offers a promising avenue for enhancing the sensitivity and effectiveness of digital health platforms. This research ventures into an uncharted territory where optical phenomena such as Brewster's Angle and Snell's Law, along with the concept of spin solitons, are metaphorically applied to address the challenge of fake news dissemination. By exploring the analogy between light refraction, reflection, and the propagation of information in digital platforms, we unveil a novel perspective on how the 'angle' at which information is presented can significantly affect its acceptance and spread. Additionally, we propose the use of tellurium nanoparticles to manage 'information waves' through mechanisms akin to plasmonic resonance and soliton dynamics. This theoretical exploration aims to bridge the gap between physical sciences and digital communication, offering insights into the development of strategies for mitigating misinformation.

Metaphors in natural language are a reflection of fundamental cognitive processes such as analogical reasoning and categorisation, and are deeply rooted in everyday communication. Metaphor understanding is therefore an essential task for large language models (LLMs). We release the Metaphor Understanding Challenge Dataset (MUNCH), designed to evaluate the metaphor understanding capabilities of LLMs. The dataset provides over 10k paraphrases for sentences containing metaphor use, as well as 1.5k instances containing inapt paraphrases. The inapt paraphrases were carefully selected to serve as control to determine whether the model indeed performs full metaphor interpretation or rather resorts to lexical similarity. All apt and inapt paraphrases were manually annotated. The metaphorical sentences cover natural metaphor uses across 4 genres (academic, news, fiction, and conversation), and they exhibit different levels of novelty. Experiments with LLaMA and GPT-3.5 demonstrate that MUNCH presents a challenging task for LLMs. The dataset is freely accessible at https://github.com/xiaoyuisrain/metaphor-understanding-challenge.

At the end of 2014, Stanford announced it was going to play host to a 100-year-long study, proposed by computer scientist Eric Horvitz, on the effects of artificial intelligence on society and how those effects "will ripple through every aspect of how people work, live and play." The study, nicknamed AI100, is mostly carried out by having a panel of experts produce a report every five years. On Thursday the first report came out, produced by 17 people, most of whom are professors in various AI-related disciplines, with a couple from companies like Microsoft of Google X. The experts break down the different effects of AI into eight different broad categories, ranging from transport to entertainment. In honor of labor day, let's focus on the area they dub "Employment and Workplace."