{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/are-llms-good-zero-shot-fallacy-classifiers","title":"Are LLMs Good Zero-Shot Fallacy Classifiers?","arxiv_id":"2410.15050","date":"2024-10-19","proceeding":null,"authors":["Fengjun Pan","Xiaobao Wu","Zongrui Li","Anh Tuan Luu"],"abstract":"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.","url_abs":"https://arxiv.org/abs/2410.15050v1","url_pdf":"https://arxiv.org/pdf/2410.15050v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"are-llms-good-zero-shot-fallacy-classifiers","repo_url":"https://github.com/panfjcharlotte98/fallacy_detection","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"misinformation","task_name":"Misinformation"}],"methods":[{"method_slug":"focus","method_name":"Focus"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2410.15050","atlas_url":"https://app.syntology.ai/?focus=2410.15050","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.15050"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/panfjcharlotte98/fallacy_detection","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":5},"by_repo_kind":{"official":{"samples":5,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"baaae1c601ba1dc7","entry":"argotario_convert_to_name","repo":"panfjcharlotte98/fallacy_detection","repo_kind":"official","path":"evaluate/convert.py","file_url":"https://github.com/panfjcharlotte98/fallacy_detection/blob/HEAD/evaluate/convert.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"baaae1c601ba1dc7"}},{"code_sha256_prefix":"b88a86c99705decd","entry":"compute_cost","repo":"panfjcharlotte98/fallacy_detection","repo_kind":"official","path":"models/gpt_based.py","file_url":"https://github.com/panfjcharlotte98/fallacy_detection/blob/HEAD/models/gpt_based.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b88a86c99705decd"}},{"code_sha256_prefix":"43b1b602a790a83e","entry":"elecdebate_convert_to_name","repo":"panfjcharlotte98/fallacy_detection","repo_kind":"official","path":"evaluate/convert.py","file_url":"https://github.com/panfjcharlotte98/fallacy_detection/blob/HEAD/evaluate/convert.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"43b1b602a790a83e"}},{"code_sha256_prefix":"5038383c322da462","entry":"logic_convert_to_name","repo":"panfjcharlotte98/fallacy_detection","repo_kind":"official","path":"evaluate/convert.py","file_url":"https://github.com/panfjcharlotte98/fallacy_detection/blob/HEAD/evaluate/convert.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5038383c322da462"}},{"code_sha256_prefix":"6581ae2c453a5a14","entry":"upsample","repo":"panfjcharlotte98/fallacy_detection","repo_kind":"official","path":"seq2seq_construction/meta_seq2seq.py","file_url":"https://github.com/panfjcharlotte98/fallacy_detection/blob/HEAD/seq2seq_construction/meta_seq2seq.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6581ae2c453a5a14"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}