Are LLMs Good Zero-Shot Fallacy Classifiers?

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Pan, Fengjun, Wu, Xiaobao, Li, Zongrui, Luu, Anh Tuan
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909356516179968
author Pan, Fengjun
Wu, Xiaobao
Li, Zongrui
Luu, Anh Tuan
author_facet Pan, Fengjun
Wu, Xiaobao
Li, Zongrui
Luu, Anh Tuan
contents Fallacies are defective arguments with faulty reasoning. Detecting and classifying them is a crucial NLP task to prevent misinformation, manipulative claims, and biased decisions. However, existing fallacy classifiers are limited by the requirement for sufficient labeled data for training, which hinders their out-of-distribution (OOD) generalization abilities. In this paper, we focus on leveraging Large Language Models (LLMs) for zero-shot fallacy classification. To elicit fallacy-related knowledge and reasoning abilities of LLMs, we propose diverse single-round and multi-round prompting schemes, applying different task-specific instructions such as extraction, summarization, and Chain-of-Thought reasoning. With comprehensive experiments on benchmark datasets, we suggest that LLMs could be potential zero-shot fallacy classifiers. In general, LLMs under single-round prompting schemes have achieved acceptable zero-shot performances compared to the best full-shot baselines and can outperform them in all OOD inference scenarios and some open-domain tasks. Our novel multi-round prompting schemes can effectively bring about more improvements, especially for small LLMs. Our analysis further underlines the future research on zero-shot fallacy classification. Codes and data are available at: https://github.com/panFJCharlotte98/Fallacy_Detection.
format Preprint
id arxiv_https___arxiv_org_abs_2410_15050
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Are LLMs Good Zero-Shot Fallacy Classifiers?
Pan, Fengjun
Wu, Xiaobao
Li, Zongrui
Luu, Anh Tuan
Computation and Language
Fallacies are defective arguments with faulty reasoning. Detecting and classifying them is a crucial NLP task to prevent misinformation, manipulative claims, and biased decisions. However, existing fallacy classifiers are limited by the requirement for sufficient labeled data for training, which hinders their out-of-distribution (OOD) generalization abilities. In this paper, we focus on leveraging Large Language Models (LLMs) for zero-shot fallacy classification. To elicit fallacy-related knowledge and reasoning abilities of LLMs, we propose diverse single-round and multi-round prompting schemes, applying different task-specific instructions such as extraction, summarization, and Chain-of-Thought reasoning. With comprehensive experiments on benchmark datasets, we suggest that LLMs could be potential zero-shot fallacy classifiers. In general, LLMs under single-round prompting schemes have achieved acceptable zero-shot performances compared to the best full-shot baselines and can outperform them in all OOD inference scenarios and some open-domain tasks. Our novel multi-round prompting schemes can effectively bring about more improvements, especially for small LLMs. Our analysis further underlines the future research on zero-shot fallacy classification. Codes and data are available at: https://github.com/panFJCharlotte98/Fallacy_Detection.
title Are LLMs Good Zero-Shot Fallacy Classifiers?
topic Computation and Language
url https://arxiv.org/abs/2410.15050