Irony Detection, Reasoning and Understanding in Zero-shot Learning

• URL: http://arxiv.org/abs/2501.16884v1
• Date: Tue, 28 Jan 2025 12:13:07 GMT
• Title: Irony Detection, Reasoning and Understanding in Zero-shot Learning
• Authors: Peiling Yi, Yuhan Xia,
• Abstract summary: Irony is a powerful figurative language (FL) on social media that can potentially mislead various NLP tasks.<n>Large language models, such as ChatGPT, are increasingly able to capture implicit and contextual information.<n>We propose a prompt engineering design framework IDADP to achieve higher irony detection accuracy, improved understanding of irony, and more effective explanations.
• Score: 0.5755004576310334
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Irony is a powerful figurative language (FL) on social media that can potentially mislead various NLP tasks, such as recommendation systems, misinformation checks, and sentiment analysis. Understanding the implicit meaning of this kind of subtle language is essential to mitigate irony's negative impact on NLP tasks. However, building models to understand irony presents a unique set of challenges, because irony is a complex form of language that often relies on context, tone, and subtle cues to convey meaning that is opposite or different from the literal interpretation. Large language models, such as ChatGPT, are increasingly able to capture implicit and contextual information. In this study, we investigate the generalization, reasoning and understanding ability of ChatGPT on irony detection across six different genre irony detection datasets. Our findings suggest that ChatGPT appears to show an enhanced language understanding and reasoning ability. But it needs to be very careful in prompt engineering design. Thus, we propose a prompt engineering design framework IDADP to achieve higher irony detection accuracy, improved understanding of irony, and more effective explanations compared to other state-of-the-art ChatGPT zero-shot approaches. And ascertain via experiments that the practice generated under the framework is likely to be the promised solution to resolve the generalization issues of LLMs.

Related papers

• Decoding Rarity: Large Language Models in the Diagnosis of Rare Diseases [1.9662978733004604]
  Large language models (LLMs) have shown promising capabilities in transforming rare disease research.<n>This paper explores the integration of LLMs in the analysis of rare diseases, highlighting significant strides and pivotal studies.
  arXiv  Detail & Related papers  (2025-05-18T15:42:15Z)
• Improving Multilingual Retrieval-Augmented Language Models through Dialectic Reasoning Argumentations [65.11348389219887]
  We introduce Dialectic-RAG (DRAG), a modular approach that evaluates retrieved information by comparing, contrasting, and resolving conflicting perspectives. We show the impact of our framework both as an in-context learning strategy and for constructing demonstrations to instruct smaller models.
  arXiv  Detail & Related papers  (2025-04-07T06:55:15Z)
• Irony in Emojis: A Comparative Study of Human and LLM Interpretation [53.66354612549173]
  This study examines the ability of GPT-4o to interpret irony in emojis.<n>By prompting GPT-4o to evaluate the likelihood of specific emojis being used to express irony on social media, we aim to bridge the gap between machine and human understanding.
  arXiv  Detail & Related papers  (2025-01-20T03:02:00Z)
• Enhancing Rhetorical Figure Annotation: An Ontology-Based Web Application with RAG Integration [0.6372911857214884]
  We develop a web application called "Find your Figure" It facilitates the identification and annotation of German rhetorical figures. In addition, we improve the user experience with Retrieval Generation (RAG)
  arXiv  Detail & Related papers  (2024-12-18T12:45:55Z)
• Detecting Emotional Incongruity of Sarcasm by Commonsense Reasoning [32.5690489394632]
  This paper focuses on sarcasm detection, which aims to identify whether given statements convey criticism, mockery, or other negative sentiment opposite to the literal meaning. Existing methods lack commonsense inferential ability when they face complex real-world scenarios, leading to unsatisfactory performance. We propose a novel framework for sarcasm detection, which conducts incongruity reasoning based on commonsense augmentation, called EICR.
  arXiv  Detail & Related papers  (2024-12-17T11:25:55Z)
• IAE: Irony-based Adversarial Examples for Sentiment Analysis Systems [4.118390893942461]
  We propose Irony-based Adversarial Examples (IAE), a method that transforms straightforward sentences into ironic ones to create adversarial text. IAE exploits the rhetorical device of irony, where the intended meaning is opposite to the literal interpretation. We demonstrate that the performance of several state-of-the-art deep learning models on sentiment analysis tasks significantly deteriorates when subjected to IAE attacks.
  arXiv  Detail & Related papers  (2024-11-12T15:01:47Z)
• Exploring Automatic Cryptographic API Misuse Detection in the Era of LLMs [60.32717556756674]
  This paper introduces a systematic evaluation framework to assess Large Language Models in detecting cryptographic misuses. Our in-depth analysis of 11,940 LLM-generated reports highlights that the inherent instabilities in LLMs can lead to over half of the reports being false positives. The optimized approach achieves a remarkable detection rate of nearly 90%, surpassing traditional methods and uncovering previously unknown misuses in established benchmarks.
  arXiv  Detail & Related papers  (2024-07-23T15:31:26Z)
• Towards Next-Generation Steganalysis: LLMs Unleash the Power of Detecting Steganography [18.7168443402118]
  Linguistic steganography provides convenient implementation to hide messages, particularly with the emergence of AI generation technology. Existing methods are limited to finding distribution differences between steganographic texts and normal texts from the aspect of symbolic statistics. This paper propose to employ human-like text processing abilities of large language models (LLMs) to realize the difference from the aspect of human perception.
  arXiv  Detail & Related papers  (2024-05-15T04:52:09Z)
• C-ICL: Contrastive In-context Learning for Information Extraction [54.39470114243744]
  c-ICL is a novel few-shot technique that leverages both correct and incorrect sample constructions to create in-context learning demonstrations. Our experiments on various datasets indicate that c-ICL outperforms previous few-shot in-context learning methods.
  arXiv  Detail & Related papers  (2024-02-17T11:28:08Z)
• FactCHD: Benchmarking Fact-Conflicting Hallucination Detection [64.4610684475899]
  FactCHD is a benchmark designed for the detection of fact-conflicting hallucinations from LLMs. FactCHD features a diverse dataset that spans various factuality patterns, including vanilla, multi-hop, comparison, and set operation. We introduce Truth-Triangulator that synthesizes reflective considerations by tool-enhanced ChatGPT and LoRA-tuning based on Llama2.
  arXiv  Detail & Related papers  (2023-10-18T16:27:49Z)
• Stance Detection with Collaborative Role-Infused LLM-Based Agents [39.75103353173015]
  Stance detection is vital for content analysis in web and social media research. However, stance detection requires advanced reasoning to infer authors' implicit viewpoints. We design a three-stage framework in which LLMs are designated distinct roles. We achieve state-of-the-art performance across multiple datasets.
  arXiv  Detail & Related papers  (2023-10-16T14:46:52Z)
• Exploring Large Language Models for Multi-Modal Out-of-Distribution Detection [67.68030805755679]
  Large language models (LLMs) encode a wealth of world knowledge and can be prompted to generate descriptive features for each class. In this paper, we propose to apply world knowledge to enhance OOD detection performance through selective generation from LLMs.
  arXiv  Detail & Related papers  (2023-10-12T04:14:28Z)
• DiPlomat: A Dialogue Dataset for Situated Pragmatic Reasoning [89.92601337474954]
  Pragmatic reasoning plays a pivotal role in deciphering implicit meanings that frequently arise in real-life conversations. We introduce a novel challenge, DiPlomat, aiming at benchmarking machines' capabilities on pragmatic reasoning and situated conversational understanding.
  arXiv  Detail & Related papers  (2023-06-15T10:41:23Z)
• Simple Linguistic Inferences of Large Language Models (LLMs): Blind Spots and Blinds [59.71218039095155]
  We evaluate language understanding capacities on simple inference tasks that most humans find trivial. We target (i) grammatically-specified entailments, (ii) premises with evidential adverbs of uncertainty, and (iii) monotonicity entailments. The models exhibit moderate to low performance on these evaluation sets.
  arXiv  Detail & Related papers  (2023-05-24T06:41:09Z)
• MAGE: Machine-generated Text Detection in the Wild [82.70561073277801]
  Large language models (LLMs) have achieved human-level text generation, emphasizing the need for effective AI-generated text detection. We build a comprehensive testbed by gathering texts from diverse human writings and texts generated by different LLMs. Despite challenges, the top-performing detector can identify 86.54% out-of-domain texts generated by a new LLM, indicating the feasibility for application scenarios.
  arXiv  Detail & Related papers  (2023-05-22T17:13:29Z)
• Towards Making the Most of ChatGPT for Machine Translation [75.576405098545]
  ChatGPT shows remarkable capabilities for machine translation (MT) Several prior studies have shown that it achieves comparable results to commercial systems for high-resource languages.
  arXiv  Detail & Related papers  (2023-03-24T03:35:21Z)
• Context-faithful Prompting for Large Language Models [51.194410884263135]
  Large language models (LLMs) encode parametric knowledge about world facts. Their reliance on parametric knowledge may cause them to overlook contextual cues, leading to incorrect predictions in context-sensitive NLP tasks. We assess and enhance LLMs' contextual faithfulness in two aspects: knowledge conflict and prediction with abstention.
  arXiv  Detail & Related papers  (2023-03-20T17:54:58Z)
• Explaining (Sarcastic) Utterances to Enhance Affect Understanding in Multimodal Dialogues [40.80696210030204]
  We propose MOSES, a deep neural network, which takes a multimodal (sarcastic) dialogue instance as an input and generates a natural language sentence as its explanation. We leverage the generated explanation for various natural language understanding tasks in a conversational dialogue setup, such as sarcasm detection, humour identification, and emotion recognition. Our evaluation shows that MOSES outperforms the state-of-the-art system for SED by an average of 2% on different evaluation metrics.
  arXiv  Detail & Related papers  (2022-11-20T18:05:43Z)
• A Survey in Automatic Irony Processing: Linguistic, Cognitive, and Multi-X Perspectives [1.6244541005112747]
  We will provide a comprehensive overview of computational irony, insights from linguistic theory and cognitive science, as well as its interactions with downstream NLP tasks and newly proposed multi-X irony processing perspectives.
  arXiv  Detail & Related papers  (2022-09-10T17:03:34Z)
• Testing the Ability of Language Models to Interpret Figurative Language [69.59943454934799]
  Figurative and metaphorical language are commonplace in discourse. It remains an open question to what extent modern language models can interpret nonliteral phrases. We introduce Fig-QA, a Winograd-style nonliteral language understanding task.
  arXiv  Detail & Related papers  (2022-04-26T23:42:22Z)
• Local Intrinsic Dimensionality Signals Adversarial Perturbations [28.328973408891834]
  Local dimensionality (LID) is a local metric that describes the minimum number of latent variables required to describe each data point. In this paper, we derive a lower-bound and an upper-bound for the LID value of a perturbed data point and demonstrate that the bounds, in particular the lower-bound, has a positive correlation with the magnitude of the perturbation.
  arXiv  Detail & Related papers  (2021-09-24T08:29:50Z)

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.