# A Logical Fallacy-Informed Framework for Argument Generation

arXiv: https://arxiv.org/abs/2408.03618 · HTML: https://mlsanity.com/paper/2408.03618/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Placed in Process reward models for reasoning, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 24 of its 49 references that are in the map.
- First posted on arXiv 7 Aug 2024.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Process reward models for reasoning](https://mlsanity.com/alignment/process-reward-models-for-reasoning/)

## Builds on (most cited first, 24 of 24)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [Self-Instruct: Aligning Language Models with Self-Generated Instructions](https://mlsanity.com/paper/2212.10560/) (2022)
- [G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment](https://mlsanity.com/paper/2303.16634/) (2023)
- [Fine-Tuning Language Models from Human Preferences](https://mlsanity.com/paper/1909.08593/) (2019)
- [Ethical and social risks of harm from Language Models](https://mlsanity.com/paper/2112.04359/) (2021)
- [Contrastive Preference Optimization: Pushing the Boundaries of LLM Performance in Machine Translation](https://mlsanity.com/paper/2401.08417/) (2024)
- [Principle-Driven Self-Alignment of Language Models from Scratch with Minimal Human Supervision](https://mlsanity.com/paper/2305.03047/) (2023)
- [Generating Datasets with Pretrained Language Models](https://mlsanity.com/paper/2104.07540/) (2021)
- [Towards Controllable Biases in Language Generation](https://mlsanity.com/paper/2005.00268/) (2020)
- [ExplaGraphs: An Explanation Graph Generation Task for Structured Commonsense Reasoning](https://mlsanity.com/paper/2104.07644/) (2021)
- [Argument Generation with Retrieval, Planning, and Realization](https://mlsanity.com/paper/1906.03717/) (2019)
- [Aspect-Controlled Neural Argument Generation](https://mlsanity.com/paper/2005.00084/) (2020)
- [Exploring the Potential of Large Language Models in Computational Argumentation](https://mlsanity.com/paper/2311.09022/) (2023)
- [Neural Argument Generation Augmented with Externally Retrieved Evidence](https://mlsanity.com/paper/1805.10254/) (2018)
- [Reason from Fallacy: Enhancing Large Language Models' Logical Reasoning through Logical Fallacy Understanding](https://mlsanity.com/paper/2404.04293/) (2024)
- [Case-Based Reasoning with Language Models for Classification of Logical Fallacies](https://mlsanity.com/paper/2301.11879/) (2023)
- [ArgU: A Controllable Factual Argument Generator](https://mlsanity.com/paper/2305.05334/) (2023)

## Built on by (most cited first, 7 of 7)

- [Do Emotions Really Affect Argument Convincingness? A Dynamic Approach with LLM-based Manipulation Checks](https://mlsanity.com/paper/2503.00024/) (2025)
- [Gaps or Hallucinations? Gazing into Machine-Generated Legal Analysis for Fine-grained Text Evaluations](https://mlsanity.com/paper/2409.09947/) (2024)
- [Emotionally Charged, Logically Blurred: AI-driven Emotional Framing Impairs Human Fallacy Detection](https://mlsanity.com/paper/2510.09695/) (2025)
- [Nuance Matters: Probing Epistemic Consistency in Causal Reasoning](https://mlsanity.com/paper/2409.00103/) (2024)
- [Joint Effects of Argumentation Theory, Audio Modality and Data Enrichment on LLM-Based Fallacy Classification](https://mlsanity.com/paper/2509.11127/) (2025)
- [ArgBench: Benchmarking LLMs on Computational Argumentation Tasks](https://mlsanity.com/paper/2604.17366/) (2026)
- [Can One-sided Arguments Lead to Response Change in Large Language Models?](https://mlsanity.com/paper/2602.06260/) (2026)

## Abstract (arXiv)

Despite the remarkable performance of Large Language Models (LLMs) in natural language processing tasks, they still struggle with generating logically sound arguments, resulting in potential risks such as spreading misinformation. To address this issue, we introduce FIPO, a fallacy-informed framework that leverages preference optimization methods to steer LLMs toward logically sound arguments. FIPO includes a classification loss, to capture the fine-grained information on fallacy types. Our results on argumentation datasets show that our method reduces the fallacy errors by up to 17.5%. Furthermore, our human evaluation results indicate that the quality of the generated arguments by our method significantly outperforms the fine-tuned baselines, as well as other preference optimization methods, such as DPO. These findings highlight the importance of ensuring models are aware of logical fallacies for effective argument generation. Our code is available at github.com/lucamouchel/Logical-Fallacies.