mlsanityData to 7 Oct 2026

ArgBench: Benchmarking LLMs on Computational Argumentation Tasks

arXiv 2604.17366 ↗First posted 19 Apr 2026cs.CL cs.AIcited by 1

Not on the map. Why?

Abstract (arXiv)

Argumentation skills are an essential toolkit for large language models (LLMs). These skills are crucial in various use cases, including self-reflection, debating collaboratively for diverse answers, and countering hate speech. In this paper, we create the first benchmark for a standardized evaluation of LLM-based approaches to computational argumentation, encompassing 33 datasets from previous work in unified form. Using the benchmark, we evaluate the generalizability of five LLM families across 46 computational argumentation tasks that cover mining arguments, assessing perspectives, assessing argument quality, reasoning about arguments, and generating arguments. On the benchmark, we conduct an extensive systematic analysis of the contribution of few-shot examples, reasoning steps, model size, and training skills to the performance of LLMs on the computational argumentation tasks in the benchmark.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 45 of its 82 references that are in the map. First posted on arXiv 19 Apr 2026.

Builds on

45 of 82 references.

References · 45

  1. 2020Measuring Massive Multitask Language Understandingcited by 7,768
  2. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,462
  3. 2018Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challengecited by 4,710
  4. 2022Self-Instruct: Aligning Language Models with Self-Generated Instructionscited by 2,674
  5. 2024Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phonecited by 1,883
  6. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,739
  7. 2023Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debatecited by 995
  8. 2020StereoSet: Measuring stereotypical bias in pretrained language modelscited by 911
  9. 2019Abductive Commonsense Reasoningcited by 300
  10. 2024Debating with More Persuasive LLMs Leads to More Truthful Answerscited by 255
  11. 2023Tree-Structured Parzen Estimator: Understanding Its Algorithm Components and Their Roles for Better Empirical Performancecited by 143
  12. 2024CriticBench: Benchmarking LLMs for Critique-Correct Reasoningcited by 88
33 more
  1. 2020From Arguments to Key Points: Towards Automatic Argument Summarizationcited by 60
  2. 2018Cross-topic Argument Mining from Heterogeneous Sources Using Attention-based Neural Networkscited by 58
  3. 2019Classification and Clustering of Arguments with Contextualized Word Embeddingscited by 57
  4. 2017The Argument Reasoning Comprehension Task: Identification and Reconstruction of Implicit Warrantscited by 55
  5. 2019Argument Generation with Retrieval, Planning, and Realizationcited by 45
  6. 2020Aspect-Controlled Neural Argument Generationcited by 43
  7. 2023Exploring the Potential of Large Language Models in Computational Argumentationcited by 42
  8. 2019Corpus Wide Argument Mining -- a Working Solutioncited by 36
  9. 2018Neural Argument Generation Augmented with Externally Retrieved Evidencecited by 34
  10. 2018Before Name-calling: Dynamics and Triggers of Ad Hominem Fallacies in Web Argumentationcited by 32
  11. 2019Are You Convinced? Choosing the More Convincing Evidence with a Siamese Networkcited by 29
  12. 2021Argument Undermining: Counter-Argument Generation by Attacking Weak Premisescited by 22
  13. 2021Scientia Potentia Est -- On the Role of Knowledge in Computational Argumentationcited by 17
  14. 2020The workweek is the best time to start a family -- A Study of GPT-2 Based Claim Generationcited by 15
  15. 2021Learning From Revisions: Quality Assessment of Claims in Argumentation at Scalecited by 14
  16. 2023Argue with Me Tersely: Towards Sentence-Level Counter-Argument Generationcited by 12
  17. 2020Creating a Domain-diverse Corpus for Theory-based Argument Quality Assessmentcited by 10
  18. 2023DiFair: A Benchmark for Disentangled Assessment of Gender Knowledge and Biascited by 9
  19. 2023To Revise or Not to Revise: Learning to Detect Improvable Claims for Argumentative Writing Supportcited by 8
  20. 2024OpenDebateEvidence: A Massive-Scale Argument Mining and Summarization Datasetcited by 8
  21. 2019Determining Relative Argument Specificity and Stance for Complex Argumentative Structurescited by 7
  22. 2023ArgU: A Controllable Factual Argument Generatorcited by 7
  23. 2024A Logical Fallacy-Informed Framework for Argument Generationcited by 7
  24. 2019Implicit Knowledge in Argumentative Texts: An Annotated Corpuscited by 6
  25. 2021Implicit Premise Generation with Discourse-aware Commonsense Knowledge Modelscited by 6
  26. 2025Limited Generalizability in Argument Mining: State-Of-The-Art Models Learn Datasets, Not Argumentscited by 5
  27. 2023Contextualizing Argument Quality Assessment with Relevant Knowledgecited by 4
  28. 2024"Let's Argue Both Sides": Argument Generation Can Force Small Models to Utilize Previously Inaccessible Reasoning Capabilitiescited by 4
  29. 2025ArgInstruct: Specialized Instruction Fine-Tuning for Computational Argumentationcited by 4
  30. 2024Assessing Open-Source Large Language Models on Argumentation Mining Subtaskscited by 3
  31. 2025ArgCMV: An Argument Summarization Benchmark for the LLM-eracited by 3
  32. 2024Consolidating Strategies for Countering Hate Speech Using Persuasive Dialoguescited by 2
  33. 2025A comprehensive study of LLM-based argument classification: from LLAMA through GPT-4o to Deepseek-R1cited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026ArgGYM: A Procedural, Engine-Verified Benchmark for Structured Defeasible Reasoningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Can formal argumentative reasoning enhance LLMs performances?
  2. 2025Can LLMs Judge Debates? Evaluating Non-Linear Reasoning via Argumentation Theory Semantics
  3. 2025Large Language Models in Argument Mining: A Survey
  4. 2026Argument Quality Assessment with Large Language Models: A Pairwise Bradley-Terry Approach
  5. 2023"I'd Like to Have an Argument, Please": Argumentative Reasoning in Large Language Models
  6. 2025Arg-LLaDA: Argument Summarization via Large Language Diffusion Models and Sufficiency-Aware Refinement
  7. 2025DS@GT at Touch'e: Large Language Models for Retrieval-Augmented Debate
  8. 2025DebateBench: A Challenging Long Context Reasoning Benchmark For Large Language Models