Anh Luu, Xiaobao Wu, Fengjun Pan, Zongrui Li
We lifted 5 functions out of this paper's own repositories and ran 0 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| panfjcharlotte98/fallacy_detection | canonical | 0 of 5 |
| Function | Status | Where it lives |
|---|---|---|
| argotario_convert_to_name | Not yet run | panfjcharlotte98/fallacy_detection/evaluate/convert.py code served (permissive licence) · get_code("baaae1c601ba1dc7") |
| compute_cost | Not yet run | panfjcharlotte98/fallacy_detection/models/gpt_based.py code served (permissive licence) · get_code("b88a86c99705decd") |
| elecdebate_convert_to_name | Not yet run | panfjcharlotte98/fallacy_detection/evaluate/convert.py code served (permissive licence) · get_code("43b1b602a790a83e") |
| logic_convert_to_name | Not yet run | panfjcharlotte98/fallacy_detection/evaluate/convert.py code served (permissive licence) · get_code("5038383c322da462") |
| upsample | Not yet run | panfjcharlotte98/fallacy_detection/seq2seq_construction/meta_seq2seq.py code served (permissive licence) · get_code("6581ae2c453a5a14") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
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 taskspecific 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 zeroshot performances compared to the best fullshot baselines and can outperform them in all OOD inference scenarios and some opendomain 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.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2410.15050")
get_code_for_paper("2410.15050")
have("2410.15050")
Connect an agent — have() is free.