Metaphor identification using large language models: A comparison of RAG, prompt engineering, and fine-tuning

• URL: http://arxiv.org/abs/2509.24866v2
• Date: Wed, 01 Oct 2025 14:06:17 GMT
• Title: Metaphor identification using large language models: A comparison of RAG, prompt engineering, and fine-tuning
• Abstract summary: This study investigates the potential of large language models (LLMs) to automate metaphor identification in full texts.<n>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.
• Score: 0.6524460254566904
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Simile Understanding in Text-to-Image Models: An Evaluation Framework [62.87595758734574]
  Recent text-to-image models (t2i models) can produce visually compelling outputs from simile prompts.<n>We propose a scalable evaluation framework for simile understanding.
  arXiv  Detail & Related papers  (2026-08-05T12:18:28Z)
• MetaphorVU: Towards Metaphorical Video Understanding [81.48044445740618]
  We propose MetaphorVU-Bench, the first systematic and comprehensive benchmark dedicated to metaphorical video understanding.<n>We find current MLLMs struggle with accurate metaphorical video understanding, lagging far behind human level, primarily due to defective cross-domain mapping.<n>Motivated by this finding, we construct a metaphor knowledge graph as mapping augmentation and propose MetaphorBoost, an inference-time enhancement framework.
  arXiv  Detail & Related papers  (2026-05-25T06:12:19Z)
• Floating or Suggesting Ideas? A Large-Scale Contrastive Analysis of Metaphorical and Literal Verb-Object Constructions [53.690096725532726]
  We analyze 297 English verb-object pairs (e.g., float idea vs. suggest idea) in 2M corpus sentences.<n>Using five NLP tools, we extract 2,293 cognitive and linguistic features capturing affective, lexical, syntactic, and discourse-level properties.<n>Cross-pair results show literal contexts have higher lexical frequency, cohesion, and structural regularity, while metaphorical contexts show greater affective load, imageability, lexical diversity, and constructional specificity.
  arXiv  Detail & Related papers  (2026-04-09T14:08:57Z)
• Unveiling LLMs' Metaphorical Understanding: Exploring Conceptual Irrelevance, Context Leveraging and Syntactic Influence [40.32545329527664]
  Large Language Models (LLMs) demonstrate advanced capabilities in knowledge integration, contextual reasoning, and creative generation.<n>This study examines LLMs' metaphor-processing abilities from three perspectives.
  arXiv  Detail & Related papers  (2025-10-05T09:45:51Z)
• In-Context Watermarks for Large Language Models [71.29952527565749]
  In-Context Watermarking (ICW) embeds watermarks into generated text solely through prompt engineering.<n>We investigate four ICW strategies at different levels of granularity, each paired with a tailored detection method.<n>Our experiments validate the feasibility of ICW as a model-agnostic, practical watermarking approach.
  arXiv  Detail & Related papers  (2025-05-22T17:24:51Z)
• Enhancing multimodal analogical reasoning with Logic Augmented Generation [1.3654846342364308]
  In this paper, we apply a logic-augmented generation (LAG) framework that leverages the explicit representation of a text through a semantic knowledge graph.<n>This method generates extended knowledge graph triples representing implicit meaning, enabling systems to reason on unlabeled multimodal data regardless of the domain.<n>The results show that this integrated approach surpasses current baselines, performs better than humans in understanding visual metaphors, and enables more explainable reasoning processes.
  arXiv  Detail & Related papers  (2025-04-15T13:47:55Z)
• Contextualize-then-Aggregate: Circuits for In-Context Learning in Gemma-2 2B [51.74607395697567]
  In-Context Learning (ICL) is an intriguing ability of large language models (LLMs)<n>We use causal interventions to identify information flow in Gemma-2 2B for five naturalistic ICL tasks.<n>We find that the model infers task information using a two-step strategy we call contextualize-then-aggregate.
  arXiv  Detail & Related papers  (2025-03-31T18:33:55Z)
• A Dual-Perspective Metaphor Detection Framework Using Large Language Models [29.18537460293431]
  We propose DMD, a novel dual-perspective framework for metaphor detection.<n>It harnesses both implicit and explicit applications of metaphor theories to guide LLMs in metaphor detection.<n>In comparison to previous methods, our framework offers more transparent reasoning processes and delivers more reliable predictions.
  arXiv  Detail & Related papers  (2024-12-23T06:50:04Z)
• VladVA: Discriminative Fine-tuning of LVLMs [67.14293827774827]
  Contrastively-trained Vision-Language Models (VLMs) like CLIP have become the de facto approach for discriminative vision-language representation learning.<n>We propose to combine "the best of both worlds": a new training approach for discriminative fine-tuning of LVLMs.
  arXiv  Detail & Related papers  (2024-12-05T17:54:27Z)
• Generative Context-aware Fine-tuning of Self-supervised Speech Models [54.389711404209415]
  We study the use of generative large language models (LLM) generated context information. We propose an approach to distill the generated information during fine-tuning of self-supervised speech models. We evaluate the proposed approach using the SLUE and Libri-light benchmarks for several downstream tasks: automatic speech recognition, named entity recognition, and sentiment analysis.
  arXiv  Detail & Related papers  (2023-12-15T15:46:02Z)
• Leveraging Pre-trained Language Model for Speech Sentiment Analysis [58.78839114092951]
  We explore the use of pre-trained language models to learn sentiment information of written texts for speech sentiment analysis. We propose a pseudo label-based semi-supervised training strategy using a language model on an end-to-end speech sentiment approach.
  arXiv  Detail & Related papers  (2021-06-11T20:15:21Z)
• Metaphor Generation with Conceptual Mappings [58.61307123799594]
  We aim to generate a metaphoric sentence given a literal expression by replacing relevant verbs. We propose to control the generation process by encoding conceptual mappings between cognitive domains. We show that the unsupervised CM-Lex model is competitive with recent deep learning metaphor generation systems.
  arXiv  Detail & Related papers  (2021-06-02T15:27:05Z)
• MERMAID: Metaphor Generation with Symbolism and Discriminative Decoding [22.756157298168127]
  Based on a theoretically-grounded connection between metaphors and symbols, we propose a method to automatically construct a parallel corpus. For the generation task, we incorporate a metaphor discriminator to guide the decoding of a sequence to sequence model fine-tuned on our parallel data. A task-based evaluation shows that human-written poems enhanced with metaphors are preferred 68% of the time compared to poems without metaphors.
  arXiv  Detail & Related papers  (2021-03-11T16:39:19Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.