Publication
Despite the remarkable performance of large language models (LLMs), they still struggle with generating logically sound arguments, resulting in potential risks such as spreading misinformation. An important factor contributing to LLMs' suboptimal performance in generating coherent arguments is their oversight of logical fallacies. To address this issue, we introduce fallacy-informed preference optimization (FIPO) that helps steer LLMs toward generating logically sound arguments. FIPO includes a classification loss to capture the fine-grained information on fallacy types. Our results on argument generation tasks show that FIPO reduces the fallacy errors by up to 17.5%. Furthermore, our human evaluation results reveal that the quality of the arguments generated by our method significantly outperforms the finetuned baselines and other preference optimization methods, such as DPO. These findings highlight the importance of ensuring models are aware of logical fallacies for effective argument generation. 1