Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.
Awesome Lists | Featured Topics | Projects
https://github.com/kashiwabyte/awesome-llm-computational-argumentation

The Hub of Computational Argumentation in the Era of LLM
https://github.com/kashiwabyte/awesome-llm-computational-argumentation
List: awesome-llm-computational-argumentation
Last synced: about 1 month ago
JSON representation
The Hub of Computational Argumentation in the Era of LLM
Host: GitHub
URL: https://github.com/kashiwabyte/awesome-llm-computational-argumentation
Owner: KashiwaByte
Created: 2024-08-15T02:13:31.000Z (4 months ago)
Default Branch: main
Last Pushed: 2024-08-28T14:28:11.000Z (4 months ago)
Last Synced: 2024-08-28T15:56:42.237Z (4 months ago)
Homepage:
Size: 8.79 KB
Stars: 2
Watchers: 1
Forks: 0
Open Issues: 0
Metadata Files:
- Readme: README.md
- Contributing: Contributing.md
Awesome Lists containing this project

ultimate-awesome - awesome-llm-computational-argumentation - The Hub of Computational Argumentation in the Era of LLM. (Other Lists / PowerShell Lists)
README

        # Awesome-LLM-Computational-Argumentation

The Hub of Computational Argumentation in the Era of LLM, where you can find surveys, papers, datasets, benchmarks, and evaluations of commonly used LLMs on computational Argumentation tasks.

## Table of Contents

- [Awesome-LLM-Computational-Argumentation](#awesome-llm-computational-argumentation)

  - [Table of Contents](#table-of-contents)

  - [Evaluation](#evaluation)

  - [Benchmark \& datasets](#benchmark--datasets)

  - [Survey](#survey)

  - [Papers](#papers)

    - [Argument Mining](#argument-mining)

    - [Argument Generation](#argument-generation)

    - [Quality Assessment](#quality-assessment)

    - [Debate For LLM](#debate-for-llm)

  - [Contributing](#contributing)

## Evaluation

![image.png](https://kashiwa-pic.oss-cn-beijing.aliyuncs.com/20240815202830.png)

## Benchmark & datasets

|  Date    | Paper                                                                                                                                                                               | Publication |

| :-----: | :---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | :---------: |

|2024-08|[DebateQA: Evaluating Question Answering on Debatable Knowledge](https://arxiv.org/abs/2408.01419)|Arxiv

|2024-06|[Assessing Good, Bad and Ugly Arguments Generated by ChatGPT: a New Dataset, its Methodology and Associated Tasks](https://arxiv.org/abs/2406.15130)|EPIA 2023

|2024-06|[Which Side Are You On? A Multi-task Dataset for End-to-End Argument Summarisation and Evaluation](https://arxiv.org/abs/2406.03151)|ACL 2024

|2024-06|[OpenDebateEvidence: A Massive-Scale Argument Mining and Summarization Dataset](https://arxiv.org/abs/2406.14657)|ACL 2024

|2024-02|[Can LLMs Speak For Diverse People? Tuning LLMs via Debate to Generate Controllable Controversial Statements](https://arxiv.org/abs/2402.10614)|	ACL 2024

|2023-12|[FREDSum: A Dialogue Summarization Corpus for French Political Debates](https://arxiv.org/abs/2312.04843)|EMNLP2023

|2023-11|[Automatic Analysis of Substantiation in Scientific Peer Reviews](https://arxiv.org/abs/2311.11967)|EMNLP 2023

|2022-06|[QT30: A Corpus of Argument and Conflict in Broadcast Debate](https://aclanthology.org/2022.lrec-1.352/)|ACL 2022

|2022-04|[Single-Turn Debate Does Not Help Humans Answer Hard Reading-Comprehension Questions](https://arxiv.org/abs/2204.05212)|ACL 2022

| 2022-03| [IAM: A Comprehensive and Large-Scale Dataset for Integrated Argument Mining Tasks](https://arxiv.org/abs/2203.12257)|ACL

|2021-02|[SummEval: Re-evaluating Summarization Evaluation](https://arxiv.org/abs/2007.12626)|tacl

|2021-01|[Learning From Revisions: Quality Assessment of Claims in Argumentation at Scale](https://arxiv.org/abs/2101.10250)|EACL 2021

|2020-12|[Transformer-Based Argument Mining for Healthcare Applications](https://ecai2020.eu/papers/1470_paper.pdf)|ECAI 2020

|2020-10|[Detecting Attackable Sentences in Arguments](https://arxiv.org/abs/2010.02660)|EMNLP 2020

|2020-10|[Unsupervised Expressive Rules Provide Explainability and Assist Human Experts Grasping New Domains](https://arxiv.org/abs/2010.09459)|EMNLP

|2020-06|[Rhetoric, Logic, and Dialectic: Advancing Theory-based Argument Quality Assessment in Natural Language Processing](https://arxiv.org/abs/2006.00843)|COLING

|2020-05|[USR: An Unsupervised and Reference Free Evaluation Metric for Dialog Generation](https://arxiv.org/abs/2005.00456)|ACL 2020

|2019-09|[A Dataset of General-Purpose Rebuttal](https://arxiv.org/abs/1909.00393)|EMNLP 2019

|2019-06|[Exploring the Role of Prior Beliefs for Argument Persuasion](https://arxiv.org/abs/1906.11301)|ACL 2018

|2019-06 |[A Corpus for Modeling User and Language Effects in Argumentation on Online Debating](https://arxiv.org/abs/1906.11310)|ACL

|2018-02|[Cross-topic Argument Mining from Heterogeneous Sources Using Attention-based Neural Networks](https://arxiv.org/abs/1802.05758)|EMNLP

|2017-04|[Recognizing Insufficiently Supported Arguments in Argumentative Essays](https://aclanthology.org/E17-1092/)|EACL

|2016-04|[Parsing Argumentation Structures in Persuasive Essays](https://arxiv.org/abs/1604.07370)|Computational Linguistics

## Survey

|  Date    | Paper                                                                                                                                                                               | Publication |

| :-----: | :---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | :---------: |

| 2023-11       | [Exploring the Potential of Large Language Models in Computational Argumentation](https://arxiv.org/abs/2311.09022)                                                                                                                      |   ACL
 

## Papers

### Argument Mining

|  Date    | Paper                                                                                                                                                                               | Publication |

| :-----: | :---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | :---------: |

|2024-07|[Argument Mining in Data Scarce Settings: Cross-lingual Transfer and Few-shot Techniques](https://arxiv.org/abs/2407.03748)|ACL 2024

|2024-06|[In-Context Learning and Fine-Tuning GPT for Argument Mining](https://arxiv.org/abs/2406.06699)|Arxiv

|2024-05|[WIBA: What Is Being Argued? A Comprehensive Approach to Argument Mining](https://arxiv.org/abs/2405.00828)|ASONAM

|2024-05|[DMON: A Simple yet Effective Approach for Argument Structure Learning](https://arxiv.org/abs/2405.01216)|	COLING 2024

|2024-04|[Exploring Key Point Analysis with Pairwise Generation and Graph Partitioning](https://arxiv.org/abs/2404.11384)|NAACL 2024

|2024-04|[A School Student Essay Corpus for Analyzing Interactions of Argumentative Structure and Quality](https://arxiv.org/abs/2404.02529)|NAACL 2024

|2024-04|[TACO -- Twitter Arguments from COnversations](https://arxiv.org/abs/2404.00406)|Arxiv

|2024-02|[Can Large Language Models perform Relation-based Argument Mining?](https://arxiv.org/abs/2402.11243)|ACL 2024

|2024-01|[End-to-End Argument Mining over Varying Rhetorical Structures](https://arxiv.org/abs/2401.11218)|Arxiv

|2023-12|[Hi-ArG: Exploring the Integration of Hierarchical Argumentation Graphs in Language Pretraining](https://arxiv.org/abs/2312.00874)|EMNLP 2023

|2023-10|[Overview of ImageArg-2023: The First Shared Task in Multimodal Argument Mining](https://arxiv.org/abs/2310.12172)|EMNLP

|2023-10|[TILFA: A Unified Framework for Text, Image, and Layout Fusion in Argument Mining](https://arxiv.org/abs/2310.05210)|EMNLP 2023

|2023-06|[Detecting Check-Worthy Claims in Political Debates, Speeches, and Interviews Using Audio Data](https://arxiv.org/abs/2306.05535)|ICASSP

|2023-05|[AQE: Argument Quadruplet Extraction via a Quad-Tagging Augmented Generative Approach](https://arxiv.org/abs/2305.19902)|ACL 2023

|2023-02|[VivesDebate-Speech: A Corpus of Spoken Argumentation to Leverage Audio Features for Argument Mining](https://arxiv.org/abs/2302.12584)|EMNLP 2023 

|2022-09|[Perturbations and Subpopulations for Testing Robustness in Token-Based Argument Unit Recognition](https://arxiv.org/abs/2209.14780)|COLING 2022

|2022-09   |[ImageArg: A Multi-modal Tweet Dataset for Image Persuasiveness Mining](https://arxiv.org/abs/2209.06416)|COLING

|2022-05|[A Holistic Framework for Analyzing the COVID-19 Vaccine Debate](https://arxiv.org/abs/2205.01817)| NAACL 2022

|2022-04|[Echoes through Time: Evolution of the Italian COVID-19 Vaccination Debate](https://arxiv.org/abs/2204.12943)|AAAI

|2022-03 |[Can Unsupervised Knowledge Transfer from Social Discussions Help Argument Mining?](https://arxiv.org/abs/2203.12881)|ACL 2022

### Argument Generation

|  Date    | Paper                                                                                                                                                                               | Publication |

| :-----: | :---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | :---------: |

| 2024-06       | [Persuasiveness of Generated Free-Text Rationales in Subjective Decisions: A Case Study on Pairwise Argument Ranking](https://arxiv.org/abs/2406.13905)                                                                                                                      |   Arxiv
 

|2023-12|[Argue with Me Tersely: Towards Sentence-Level Counter-Argument Generation](https://arxiv.org/abs/2312.13608)|EMNLP 2023

|2023-10|[From Values to Opinions: Predicting Human Behaviors and Stances Using Value-Injected Large Language Models](https://arxiv.org/abs/2310.17857)|	EMNLP 2023

|2023-09|[Claim Optimization in Computational Argumentation](https://arxiv.org/abs/2212.08913)| INLG 2023

|2023-07|[DebateKG: Automatic Policy Debate Case Creation with Semantic Knowledge Graphs](https://arxiv.org/abs/2307.04090)|EMNLP 2023

|2023-01|[Conclusion-based Counter-Argument Generation](https://arxiv.org/abs/2301.09911)|eacl-23

|2022-10|[MOCHA: A Multi-Task Training Approach for Coherent Text Generation from Cognitive Perspective](https://arxiv.org/abs/2210.14650)|EMNLP 2022

|2022-05 |[RSTGen: Imbuing Fine-Grained Interpretable Control into Long-FormText Generators](https://arxiv.org/abs/2205.12590) |NAACL 2022

|2022-03|[The Moral Debater: A Study on the Computational Generation of Morally Framed Arguments](https://arxiv.org/abs/2203.14563)| ACL 2022

### Quality Assessment

|  Date    | Paper                                                                                                                                                                               | Publication |

| :-----: | :---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | :---------: |

|2024-06|[Assessing Good, Bad and Ugly Arguments Generated by ChatGPT: a New Dataset, its Methodology and Associated Tasks](https://arxiv.org/abs/2406.15130)|EPIA 2023

| 2024-04       | [Can Language Models Recognize Convincing Arguments?](https://arxiv.org/abs/2404.00750)                                                                                                                      |   Arxiv

|2024-03|[Argument Quality Assessment in the Age of Instruction-Following Large Language Models](https://arxiv.org/abs/2403.16084)|COLING 2024

|2023-11|[Automatic Analysis of Substantiation in Scientific Peer Reviews](https://arxiv.org/abs/2311.11967)|EMNLP 2023 

|2023-05|[Contextualizing Argument Quality Assessment with Relevant Knowledge](https://arxiv.org/abs/2305.12280)|NAACL 2024	

|2023-01|[Conclusion-based Counter-Argument Generation](https://arxiv.org/abs/2301.09911)|eacl-23

|2022-12|[Claim Optimization in Computational Argumentation](https://arxiv.org/abs/2212.08913)| INLG 2023

|2022-03|[Automatic Debate Evaluation with Argumentation Semantics and Natural Language Argument Graph Networks](https://arxiv.org/abs/2203.14647)|EMNLP 2023

|2021-10|[Assessing the Sufficiency of Arguments through Conclusion Generation](https://arxiv.org/abs/2110.13495)|EMNLP 2021

|2020-12|[Rhetoric, Logic, and Dialectic: Advancing Theory-based Argument Quality Assessment in Natural Language Processing](https://arxiv.org/abs/2006.00843)|COLING 20

|2020-10|[Exploring the Role of Argument Structure in Online Debate Persuasion](https://arxiv.org/abs/2010.03538)|EMNLP 2020

|2019-09|[A Large-scale Dataset for Argument Quality Ranking: Construction and Analysis](https://arxiv.org/abs/1911.11408)| AAAI 2020

|2019-09|[Automatic Argument Quality Assessment -- New Datasets and Methods](https://arxiv.org/abs/1909.01007)|EMNLP 2019

### Debate For LLM 

|  Date    | Paper                                                                                                                                                                               | Publication |

| :-----: | :---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | :---------: |

|2024-08|[Can LLMs Beat Humans in Debating? A Dynamic Multi-agent Framework for Competitive Debate](https://arxiv.org/abs/2408.04472)|Arxiv

|2024-06|[An Empirical Analysis on Large Language Models in Debate Evaluation](https://arxiv.org/abs/2406.00050)|ACL 2024

| 2024-05       |[DEBATE: Devil's Advocate-Based Assessment and Text Evaluation](https://arxiv.org/abs/2405.09935)|Arxiv

|2024-03|[Debatrix: Multi-dimensional Debate Judge with Iterative Chronological Analysis Based on LLM](https://arxiv.org/abs/2403.08010)|ACL 2024

|2024-03|[A Picture Is Worth a Graph: A Blueprint Debate Paradigm for Multimodal Reasoning](https://arxiv.org/abs/2403.14972)|ACM Multimedia

| 2024-02       | [Debating with More Persuasive LLMs Leads to More Truthful Answers](https://arxiv.org/abs/2402.06782) |   ICML 2024

|2024-02|[Can LLMs Speak For Diverse People? Tuning LLMs via Debate to Generate Controllable Controversial Statements](https://arxiv.org/abs/2402.10614)|	ACL 2024

|2024-01|[Can Large Language Models be Trusted for Evaluation? Scalable Meta-Evaluation of LLMs as Evaluators via Agent Debate](https://arxiv.org/abs/2401.16788)|Arxiv

|2024-01|[Combating Adversarial Attacks with Multi-Agent Debate](https://arxiv.org/abs/2401.05998)|Arxiv

|2024-01|[Towards Explainable Harmful Meme Detection through Multimodal Debate between Large Language Models](https://arxiv.org/abs/2401.13298)|ACM Web

|2023-12|[Learning to Break: Knowledge-Enhanced Reasoning in Multi-Agent Debate System](https://github.com/FutureForMe/MADKE)|Arxiv

|2023-12|[Recourse under Model Multiplicity via Argumentative Ensembling (Technical Report)](https://arxiv.org/abs/2312.15097)|AAMAS 2024

|2023-11|[Should we be going MAD? A Look at Multi-Agent Debate Strategies for LLMs](https://arxiv.org/abs/2311.17371)|Arixv

|2023-11|[Debate Helps Supervise Unreliable Experts](https://arxiv.org/abs/2311.08702)|Arxiv

|2023-11|[Scalable AI Safety via Doubly-Efficient Debate](https://arxiv.org/abs/2311.14125)|Arxiv

|2023-10|[From Values to Opinions: Predicting Human Behaviors and Stances Using Value-Injected Large Language Models](https://arxiv.org/abs/2310.17857)|EMNLP 2023

|2023-10|[Let Models Speak Ciphers: Multiagent Debate through Embeddings](https://arxiv.org/abs/2310.06272)|ICLR 2024

|2023-08|[ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate](https://arxiv.org/abs/2308.07201)| ICLR 2024

|2023-05|[Can ChatGPT Defend its Belief in Truth? Evaluating LLM Reasoning via Debate](https://arxiv.org/abs/2305.13160)|EMNLP 2023

|2023-05|[Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://arxiv.org/abs/2305.14325)|ICML 2024

|2023-05|[Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate](https://arxiv.org/abs/2305.19118)|Arxiv

|2023-05|[Examining Inter-Consistency of Large Language Models Collaboration: An In-depth Analysis via Debate](https://arxiv.org/abs/2305.11595)|	EMNLP 2023

|2022-10|[The Debate Over Understanding in AI's Large Language Models](https://arxiv.org/abs/2210.13966)|Arixv

|2022-03|[The Moral Debater: A Study on the Computational Generation of Morally Framed Arguments](https://arxiv.org/abs/2203.14563)|ACL 2022

|2021-10|[Project Debater APIs: Decomposing the AI Grand Challenge](https://arxiv.org/abs/2110.01029)|EMNLP 2021 

## Contributing