Challenge: Argument generation is crucial in daily life and has numerous online and offline applications.
Approach: They propose a fallacy-informed preference optimization that includes a classification loss to capture the fine-grained information on fallacy types to help LLMs generate logically sound arguments.
Outcome: The proposed method reduces fallacy errors by 17.5% on argument generation tasks and outperforms fine-tuned baselines and other preference optimization methods, such as DPO.

Similar Papers

Reason from Fallacy: Enhancing Large Language Models’ Logical Reasoning through Logical Fallacy Understanding (2024.findings-naacl)

Copied to clipboard

Challenge: Large Language Models (LLMs) have demonstrated good performance in many reasoning tasks, but struggle with some more complex reasoning tasks including logical reasoning.
Approach: They propose five concrete tasks from three cognitive dimensions of WHAT, WHY, and HOW to evaluate LLMs’ capability of logical fallacy understanding.
Outcome: The proposed dataset can be used to evaluate LLMs’ LFU capability and to fine-tune LLM models to obtain significantly enhanced performance on logical reasoning.
Large Language Models Are Better Logical Fallacy Reasoners with Counterargument, Explanation, and Goal-Aware Prompt Formulation (2025.findings-naacl)

Copied to clipboard

Challenge: Recent large language models have demonstrated improved processing of complex language, but detecting logical fallacies remains a challenge.
Approach: They propose a prompt formulation approach for logical fallacy detection that integrates contextual information into input text and queries for validity within the argument’s context.
Outcome: The proposed approach improves over state-of-the-art models by 0.57 in F1-scores and 0.45 in fine-tuned models.
Improving Argument Effectiveness Across Ideologies using Instruction-tuned Large Language Models (2024.findings-emnlp)

Copied to clipboard

Challenge: a study finds that different political ideologies hold different worldviews, which leads to contentious debates . argument effectiveness is improved by using instruction-tuned large language models .
Approach: They propose to use instruction-tuned large language models to turn ineffective arguments into effective arguments for people with certain ideologies.
Outcome: The proposed methods improve argument effectiveness for liberals by rewriting arguments using three LLM methods.
How Susceptible Are LLMs to Logical Fallacies? (2024.lrec-main)

Copied to clipboard

Challenge: Recent studies have focused on LLMs' reasoning abilities, but their rational thinking capacity is not as robust as that of other NLP downstream tasks.
Approach: They propose a diagnostic benchmark to assess the robustness of Large Language Models against logical fallacies by comparing their performance against a scenario where the persuader employs logical fallsacie.
Outcome: The proposed benchmark compares the performance of LLMs in debates on controversial topics against logical fallacies.
Flee the Flaw: Annotating the Underlying Logic of Fallacious Arguments Through Templates and Slot-filling (2024.emnlp-main)

Copied to clipboard

Challenge: Prior work on quality assessment has focused on numerical scoring and fallacy type-labeling tasks, without aiming to analyze fallacy logic structures.
Approach: They propose four sets of explainable templates for common informal logical fallacies designed to explicate a fallacy’s implicit logic.
Outcome: The proposed models achieve a high agreement score and reasonable coverage 83% on 400 fallacious arguments and state-of-the-art language models struggle with detecting fallacy templates (0.47 accuracy).
Emotionally Charged, Logically Blurred: AI-driven Emotional Framing Impairs Human Fallacy Detection (2026.eacl-long)

Copied to clipboard

Challenge: Existing computational approaches focus on logical structures of fallacies and argumentation schemes, ignoring the emotional dimension of argumentation.
Approach: They propose to use large language models to systematically change emotional appeals in fallacious arguments by using a computational approach.
Outcome: The proposed method reduces fallacy detection by 14.5% on average on human arguments with enjoyment over fear or sadness.
Conclusion-based Counter-Argument Generation (2023.eacl-main)

Copied to clipboard

Challenge: Existing work on the automatic generation of natural language counter-arguments does not address the relation to the conclusion, possibly because many arguments leave their conclusion implicit.
Approach: They propose a multitask approach that jointly learns to generate both the conclusion and the counter of an input argument.
Outcome: The proposed approach generates more relevant and stance-adhering counters than strong baselines.
Improving LLM Generations via Fine-Grained Self-Endorsement (2024.findings-acl)

Copied to clipboard

Challenge: Recent large language models (LLMs) have demonstrated remarkable capabilities but can still fail frequently on knowledge-intensive tasks.
Approach: They propose a self-endorsement framework that leverages fine-grained fact-level comparisons across multiple sampled responses.
Outcome: The proposed framework can improve factuality of generations with simple prompts across scales of LLMs.
Argument Generation with Retrieval, Planning, and Realization (P19-1)

Copied to clipboard

Challenge: a novel argument generation framework is used to generate counter-arguments . CANDELA uses a text planning decoder to retrieve arguments of different perspectives .
Approach: They propose a powerful retrieval system and a novel two-step argument generation framework . they use a retrieval-based retrieval platform indexed with 12 million articles from Wikipedia .
Outcome: The proposed framework yields higher BLEU, ROUGE, and METEOR scores than state-of-the-art models.
Argument Mining with Fine-Tuned Large Language Models (2025.coling-main)

Copied to clipboard

Challenge: Argument Mining (AM) pipelines use fine-tuned large language models (LLMs) . initial approaches employ supervised machine learning algorithms, such as Maximum Entropy classifiers and Logistic Regressions.
Approach: They propose to model the three main AM sub-tasks as text generation tasks and fine-tune eight popular quantized and non-quantized large language models (LLMs) on the benchmark PE, AbstRCT, and CDCP datasets.
Outcome: The proposed pipeline achieves state-of-the-art across all AM sub-tasks and datasets, showing significant improvements over previous benchmarks.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations